Björn Schuller

Rui Liu, Berrak Sisman, Björn Schuller et al.

Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ranking function based on Support Vector Machine (SVM) was proposed to predict emotion strength for emotional speech corpus. However, the trained ranking function doesn't generalize to new domains, which limits the scope of applications, especially for out-of-domain or unseen speech. In this paper, we propose a data-driven deep learning model, i.e. StrengthNet, to improve the generalization of emotion strength assessment for seen and unseen speech. This is achieved by the fusion of emotional data from various domains. We follow a multi-task learning network architecture that includes an acoustic encoder, a strength predictor, and an auxiliary emotion predictor. Experiments show that the predicted emotion strength of the proposed StrengthNet is highly correlated with ground truth scores for both seen and unseen speech. We release the source codes at: https://github.com/ttslr/StrengthNet.

Alice Baird, Panagiotis Tzirakis, Gauthier Gidel et al.

The ICML Expressive Vocalization (ExVo) Competition is focused on understanding and generating vocal bursts: laughs, gasps, cries, and other non-verbal vocalizations that are central to emotional expression and communication. ExVo 2022, includes three competition tracks using a large-scale dataset of 59,201 vocalizations from 1,702 speakers. The first, ExVo-MultiTask, requires participants to train a multi-task model to recognize expressed emotions and demographic traits from vocal bursts. The second, ExVo-Generate, requires participants to train a generative model that produces vocal bursts conveying ten different emotions. The third, ExVo-FewShot, requires participants to leverage few-shot learning incorporating speaker identity to train a model for the recognition of 10 emotions conveyed by vocal bursts. This paper describes the three tracks and provides performance measures for baseline models using state-of-the-art machine learning strategies. The baseline for each track is as follows, for ExVo-MultiTask, a combined score, computing the harmonic mean of Concordance Correlation Coefficient (CCC), Unweighted Average Recall (UAR), and inverted Mean Absolute Error (MAE) ($S_{MTL}$) is at best, 0.335 $S_{MTL}$; for ExVo-Generate, we report Fréchet inception distance (FID) scores ranging from 4.81 to 8.27 (depending on the emotion) between the training set and generated samples. We then combine the inverted FID with perceptual ratings of the generated samples ($S_{Gen}$) and obtain 0.174 $S_{Gen}$; and for ExVo-FewShot, a mean CCC of 0.444 is obtained.

Anna Hlédiková, Dominika Woszczyk, Alican Akman et al.

Dementia is a growing problem as our society ages, and detection methods are often invasive and expensive. Recent deep-learning techniques can offer a faster diagnosis and have shown promising results. However, they require large amounts of labelled data which is not easily available for the task of dementia detection. One effective solution to sparse data problems is data augmentation, though the exact methods need to be selected carefully. To date, there has been no empirical study of data augmentation on Alzheimer's disease (AD) datasets for NLP and speech processing. In this work, we investigate data augmentation techniques for the task of AD detection and perform an empirical evaluation of the different approaches on two kinds of models for both the text and audio domains. We use a transformer-based model for both domains, and SVM and Random Forest models for the text and audio domains, respectively. We generate additional samples using traditional as well as deep learning based methods and show that data augmentation improves performance for both the text- and audio-based models and that such results are comparable to state-of-the-art results on the popular ADReSS set, with carefully crafted architectures and features.

Alice Baird, Panagiotis Tzirakis, Jeffrey A. Brooks et al.

The ACII Affective Vocal Bursts Workshop & Competition is focused on understanding multiple affective dimensions of vocal bursts: laughs, gasps, cries, screams, and many other non-linguistic vocalizations central to the expression of emotion and to human communication more generally. This year's competition comprises four tracks using a large-scale and in-the-wild dataset of 59,299 vocalizations from 1,702 speakers. The first, the A-VB-High task, requires competition participants to perform a multi-label regression on a novel model for emotion, utilizing ten classes of richly annotated emotional expression intensities, including; Awe, Fear, and Surprise. The second, the A-VB-Two task, utilizes the more conventional 2-dimensional model for emotion, arousal, and valence. The third, the A-VB-Culture task, requires participants to explore the cultural aspects of the dataset, training native-country dependent models. Finally, for the fourth task, A-VB-Type, participants should recognize the type of vocal burst (e.g., laughter, cry, grunt) as an 8-class classification. This paper describes the four tracks and baseline systems, which use state-of-the-art machine learning methods. The baseline performance for each track is obtained by utilizing an end-to-end deep learning model and is as follows: for A-VB-High, a mean (over the 10-dimensions) Concordance Correlation Coefficient (CCC) of 0.5687 CCC is obtained; for A-VB-Two, a mean (over the 2-dimensions) CCC of 0.5084 is obtained; for A-VB-Culture, a mean CCC from the four cultures of 0.4401 is obtained; and for A-VB-Type, the baseline Unweighted Average Recall (UAR) from the 8-classes is 0.4172 UAR.

Nikolai Körber, Eduard Kromer, Andreas Siebert et al.

We introduce PerCo (SD), a perceptual image compression method based on Stable Diffusion v2.1, targeting the ultra-low bit range. PerCo (SD) serves as an open and competitive alternative to the state-of-the-art method PerCo, which relies on a proprietary variant of GLIDE and remains closed to the public. In this work, we review the theoretical foundations, discuss key engineering decisions in adapting PerCo to the Stable Diffusion ecosystem, and provide a comprehensive comparison, both quantitatively and qualitatively. On the MSCOCO-30k dataset, PerCo (SD) demonstrates improved perceptual characteristics at the cost of higher distortion. We partly attribute this gap to the different model capacities being used (866M vs. 1.4B). We hope our work contributes to a deeper understanding of the underlying mechanisms and paves the way for future advancements in the field. Code and trained models will be released at https://github.com/Nikolai10/PerCo.

Oliver Schrüfer, Manuel Milling, Felix Burkhardt et al.

Uncertainty Quantification (UQ) is an important building block for the reliable use of neural networks in real-world scenarios, as it can be a useful tool in identifying faulty predictions. Speech emotion recognition (SER) models can suffer from particularly many sources of uncertainty, such as the ambiguity of emotions, Out-of-Distribution (OOD) data or, in general, poor recording conditions. Reliable UQ methods are thus of particular interest as in many SER applications no prediction is better than a faulty prediction. While the effects of label ambiguity on uncertainty are well documented in the literature, we focus our work on an evaluation of UQ methods for SER under common challenges in real-world application, such as corrupted signals, and the absence of speech. We show that simple UQ methods can already give an indication of the uncertainty of a prediction and that training with additional OOD data can greatly improve the identification of such signals.

Björn Schuller, Adria Mallol-Ragolta, Alejandro Peña Almansa et al.

The dawn of Foundation Models has on the one hand revolutionised a wide range of research problems, and, on the other hand, democratised the access and use of AI-based tools by the general public. We even observe an incursion of these models into disciplines related to human psychology, such as the Affective Computing domain, suggesting their affective, emerging capabilities. In this work, we aim to raise awareness of the power of Foundation Models in the field of Affective Computing by synthetically generating and analysing multimodal affective data, focusing on vision, linguistics, and speech (acoustics). We also discuss some fundamental problems, such as ethical issues and regulatory aspects, related to the use of Foundation Models in this research area.

Nikolai Körber, Eduard Kromer, Andreas Siebert et al.

We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditional pre-trained semantic segmentation-guided discriminator, which provides both spatially and semantically-aware gradient feedback to the generator, conditioned on the latent image distribution, and ii) Output Residual Prediction (ORP), a retrofit solution for multi-realism image compression that allows control over the synthesis process by adjusting the impact of the residual between an MSE-optimized and GAN-optimized decoder output on the GAN-based reconstruction. Together, EGIC forms a powerful codec, outperforming state-of-the-art diffusion and GAN-based methods (e.g., HiFiC, MS-ILLM, and DIRAC-100), while performing almost on par with VTM-20.0 on the distortion end. EGIC is simple to implement, very lightweight, and provides excellent interpolation characteristics, which makes it a promising candidate for practical applications targeting the low bit range.

Xin Jing, Andreas Triantafyllopoulos, Jiadong Wang et al.

Recent advancements in speech captioning models have enabled the generation of rich, fine-grained captions for emotional speech. However, the evaluation of such captions remains a critical bottleneck: traditional N-gram metrics fail to capture semantic nuances, while LLM judges often suffer from reasoning inconsistency and context-collapse when processing long-form descriptions. In this work, we propose EmoSURA, a novel evaluation framework that shifts the paradigm from holistic scoring to atomic verification. EmoSURA decomposes complex captions into Atomic Perceptual Units, which are self-contained statements regarding vocal or emotional attributes, and employs an audio-grounded verification mechanism to validate each unit against the raw speech signal. Furthermore, we address the scarcity of standardized evaluation resources by introducing SURABench, a carefully balanced and stratified benchmark. Our experiments show that EmoSURA achieves a positive correlation with human judgments, offering a more reliable assessment for long-form captions compared to traditional metrics, which demonstrated negative correlations due to their sensitivity to caption length.

He Hu, Tengjin Weng, Zebang Cheng et al.

Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, where understanding human emotions is essential. However, existing benchmarks mainly formulate emotion understanding as a static recognition problem, leaving it largely unclear whether current MLLMs can understand emotion as a dynamic process that evolves, shifts between states, and unfolds across diverse social contexts. To bridge this gap, we present EmoTrans, a benchmark for evaluating emotion dynamics understanding in multimodal videos. EmoTrans contains 1,000 carefully collected and manually annotated video clips, covering 12 real-world scenarios, and further provides over 3,000 task-specific question-answer (QA) pairs for fine-grained evaluation. The benchmark introduces four tasks, namely Emotion Change Detection (ECD), Emotion State Identification (ESI), Emotion Transition Reasoning (ETR), and Next Emotion Prediction (NEP), forming a progressive evaluation framework from coarse-grained detection to deeper reasoning and prediction. We conduct a comprehensive evaluation of 18 state-of-the-art MLLMs on EmoTrans and obtain two main findings. First, although current MLLMs show relatively stronger performance on coarse-grained emotion change detection, they still struggle with fine-grained emotion dynamics modeling. Second, socially complex settings, especially multi-person scenarios, remain substantially challenging, while reasoning-oriented variants do not consistently yield clear improvements. To facilitate future research, we publicly release the benchmark, evaluation protocol, and code at https://github.com/Emo-gml/EmoTrans.

Nina Peire, Yupei Li, Björn Schuller

Generalisation to unseen subjects in EEG-based emotion classification remains a challenge due to high inter-and intra-subject variability. Continual learning (CL) poses a promising solution by learning from a sequence of tasks while mitigating catastrophic forgetting. Regularisation-based CL approaches, such as Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), and Memory Aware Synapses (MAS), are commonly used as baselines in EEG-based CL studies, yet their suitability for this problem remains underexplored. This study theoretically and empirically finds that regularisation-based CL methods show limited performance for EEG-based emotion classification on the DREAMER and SEED datasets. We identify a fundamental misalignment in the stability-plasticity trade-off, where regularisation-based methods prioritise mitigating catastrophic forgetting (backward transfer) over adapting to new subjects (forward transfer). We investigate this limitation under subject-incremental sequences and observe that: (1) the heuristics for estimating parameter importance become less reliable under noisy data and covariate shift, (2) gradients on parameters deemed important by these heuristics often interfere with gradient updates required for new subjects, moving optimisation away from the minimum, (3) importance values accumulated across tasks over-constrain the model, and (4) performance is sensitive to subject order. Forward transfer showed no statistically significant improvement over sequential fine-tuning (p > 0.05 across approaches and datasets). The high variability of EEG signals means past subjects provide limited value to future subjects. Regularisation-based continual learning approaches are therefore limited for robust generalisation to unseen subjects in EEG-based emotion classification.

Nikolai Körber, Eduard Kromer, Andreas Siebert et al.

We introduce PerCoV2, a novel and open ultra-low bit-rate perceptual image compression system designed for bandwidth- and storage-constrained applications. Building upon prior work by Careil et al., PerCoV2 extends the original formulation to the Stable Diffusion 3 ecosystem and enhances entropy coding efficiency by explicitly modeling the discrete hyper-latent image distribution. To this end, we conduct a comprehensive comparison of recent autoregressive methods (VAR and MaskGIT) for entropy modeling and evaluate our approach on the large-scale MSCOCO-30k benchmark. Compared to previous work, PerCoV2 (i) achieves higher image fidelity at even lower bit-rates while maintaining competitive perceptual quality, (ii) features a hybrid generation mode for further bit-rate savings, and (iii) is built solely on public components. Code and trained models will be released at https://github.com/Nikolai10/PerCoV2.

Maurice Gerczuk, Shahin Amiriparian, Sandra Ottl et al.

In this manuscript, the topic of multi-corpus Speech Emotion Recognition (SER) is approached from a deep transfer learning perspective. A large corpus of emotional speech data, EmoSet, is assembled from a number of existing SER corpora. In total, EmoSet contains 84181 audio recordings from 26 SER corpora with a total duration of over 65 hours. The corpus is then utilised to create a novel framework for multi-corpus speech emotion recognition, namely EmoNet. A combination of a deep ResNet architecture and residual adapters is transferred from the field of multi-domain visual recognition to multi-corpus SER on EmoSet. Compared against two suitable baselines and more traditional training and transfer settings for the ResNet, the residual adapter approach enables parameter efficient training of a multi-domain SER model on all 26 corpora. A shared model with only $3.5$ times the number of parameters of a model trained on a single database leads to increased performance for 21 of the 26 corpora in EmoSet. Measured by McNemar's test, these improvements are further significant for ten datasets at $p<0.05$ while there are just two corpora that see only significant decreases across the residual adapter transfer experiments. Finally, we make our EmoNet framework publicly available for users and developers at https://github.com/EIHW/EmoNet. EmoNet provides an extensive command line interface which is comprehensively documented and can be used in a variety of multi-corpus transfer learning settings.

Shuo Liu, Gil Keren, Björn Schuller

N-HANS is a Python toolkit for in-the-wild audio enhancement, including speech, music, and general audio denoising, separation, and selective noise or source suppression. The functionalities are realised based on two neural network models sharing the same architecture, but trained separately. The models are comprised of stacks of residual blocks, each conditioned on additional speech or environmental noise recordings for adapting to different unseen speakers or environments in real life. In addition to a Python API, a command line interface is provided to researchers and developers, both of which are documented at https://github.com/N-HANS/N-HANS. Experimental results indicate that N-HANS achieves outstanding performance, and ensure its reliable usage in real-life audio and speech-related tasks, reaching very high audio and speech quality.

Johannes Wagner, Tobias Baur, Yue Zhang et al.

Scientific disciplines, such as Behavioural Psychology, Anthropology and recently Social Signal Processing are concerned with the systematic exploration of human behaviour. A typical work-flow includes the manual annotation (also called coding) of social signals in multi-modal corpora of considerable size. For the involved annotators this defines an exhausting and time-consuming task. In the article at hand we present a novel method and also provide the tools to speed up the coding procedure. To this end, we suggest and evaluate the use of Cooperative Machine Learning (CML) techniques to reduce manual labelling efforts by combining the power of computational capabilities and human intelligence. The proposed CML strategy starts with a small number of labelled instances and concentrates on predicting local parts first. Afterwards, a session-independent classification model is created to finish the remaining parts of the database. Confidence values are computed to guide the manual inspection and correction of the predictions. To bring the proposed approach into application we introduce NOVA - an open-source tool for collaborative and machine-aided annotations. In particular, it gives labellers immediate access to CML strategies and directly provides visual feedback on the results. Our experiments show that the proposed method has the potential to significantly reduce human labelling efforts.

Michael Freitag, Shahin Amiriparian, Sergey Pugachevskiy et al.

auDeep is a Python toolkit for deep unsupervised representation learning from acoustic data. It is based on a recurrent sequence to sequence autoencoder approach which can learn representations of time series data by taking into account their temporal dynamics. We provide an extensive command line interface in addition to a Python API for users and developers, both of which are comprehensively documented and publicly available at https://github.com/auDeep/auDeep. Experimental results indicate that auDeep features are competitive with state-of-the art audio classification.

Gil Keren, Sivan Sabato, Björn Schuller

We consider neural network training, in applications in which there are many possible classes, but at test-time, the task is a binary classification task of determining whether the given example belongs to a specific class, where the class of interest can be different each time the classifier is applied. For instance, this is the case for real-time image search. We define the Single Logit Classification (SLC) task: training the network so that at test-time, it would be possible to accurately identify whether the example belongs to a given class in a computationally efficient manner, based only on the output logit for this class. We propose a natural principle, the Principle of Logit Separation, as a guideline for choosing and designing losses suitable for the SLC. We show that the cross-entropy loss function is not aligned with the Principle of Logit Separation. In contrast, there are known loss functions, as well as novel batch loss functions that we propose, which are aligned with this principle. In total, we study seven loss functions. Our experiments show that indeed in almost all cases, losses that are aligned with the Principle of Logit Separation obtain at least 20% relative accuracy improvement in the SLC task compared to losses that are not aligned with it, and sometimes considerably more. Furthermore, we show that fast SLC does not cause any drop in binary classification accuracy, compared to standard classification in which all logits are computed, and yields a speedup which grows with the number of classes. For instance, we demonstrate a 10x speedup when the number of classes is 400,000. Tensorflow code for optimizing the new batch losses is publicly available at https://github.com/cruvadom/Logit Separation.

Gil Keren, Björn Schuller

Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by feeding patches of the data into a recurrent neural network and using the outputs or hidden states of the recurrent units to compute the extracted features. By doing so, we exploit the fact that a window containing a few frames of the sequential data is a sequence itself and this additional structure might encapsulate valuable information. In addition, we allow for more steps of computation in the feature extraction process, which is potentially beneficial as an affine function followed by a non-linearity can result in too simple features. Using our convolutional recurrent layers we obtain an improvement in performance in two audio classification tasks, compared to traditional convolutional layers. Tensorflow code for the convolutional recurrent layers is publicly available in https://github.com/cruvadom/Convolutional-RNN.

Mohamed Mady, Johannes Reschke, Björn Schuller

AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on HC3 PLUS and calibrate a single decision threshold by maximising balanced accuracy on held-out validation; this threshold is then kept fixed for all downstream test distributions, revealing domain- and generator-dependent error asymmetries under shift. We evaluate in-domain on HC3 PLUS, under cross-dataset transfer to the multi-domain, multi-generator M4 benchmark, and on the external AI-Text-Detection-Pile. Although base models achieve near-ceiling in-domain performance (up to 99.5% balanced accuracy), performance under shift is brittle and strongly model-dependent. Feature augmentation via attention-based linguistic feature fusion improves transfer, with our best model (DeBERTa-v3-base+FeatAttn) achieving 85.9% balanced accuracy on M4. Multi-seed experiments confirm high stability. Under the same fixed-threshold protocol, our model outperforms strong zero-shot baselines by up to +7.22 points. Category-level ablations further show that readability and vocabulary features contribute most to robustness under shift. Overall, these results demonstrate that feature augmentation and a modern DeBERTa backbone significantly outperform earlier BERT/RoBERTa models, while the fixed-threshold protocol provides a more realistic and informative assessment of practical detector robustness.

Tomisin Ogunnubi, Yupei Li, Björn Schuller

Speech Emotion Recognition (SER) systems have growing applications in sensitive domains such as mental health and education, where biased predictions can cause harm. Traditional fairness metrics, such as Equalised Odds and Demographic Parity, often overlook the joint dependency between demographic attributes and model predictions. We propose a fairness modelling approach for SER that explicitly captures allocative bias by learning the joint relationship between demographic attributes and model error. We validate our fairness metric on synthetic data, then apply it to evaluate HuBERT and WavLM models finetuned on the CREMA-D dataset. Our results indicate that the proposed fairness model captures more mutual information between protected attributes and biases and quantifies the absolute contribution of individual attributes to bias in SSL-based SER models. Additionally, our analysis reveals indications of gender bias in both HuBERT and WavLM.

Changzeng Fu, Zelin Fu, Qi Zhang et al.

Depression is a widespread mental health issue affecting diverse age groups, with notable prevalence among college students and the elderly. However, existing datasets and detection methods primarily focus on young adults, neglecting the broader age spectrum and individual differences that influence depression manifestation. Current approaches often establish a direct mapping between multimodal data and depression indicators, failing to capture the complexity and diversity of depression across individuals. This challenge includes two tracks based on age-specific subsets: Track 1 uses the MPDD-Elderly dataset for detecting depression in older adults, and Track 2 uses the MPDD-Young dataset for detecting depression in younger participants. The Multimodal Personality-aware Depression Detection (MPDD) Challenge aims to address this gap by incorporating multimodal data alongside individual difference factors. We provide a baseline model that fuses audio and video modalities with individual difference information to detect depression manifestations in diverse populations. This challenge aims to promote the development of more personalized and accurate de pression detection methods, advancing mental health research and fostering inclusive detection systems. More details are available on the official challenge website: https://hacilab.github.io/MPDDChallenge.github.io.

Jihwan Lee, Kevin Huang, Kleanthis Avramidis et al.

We present a model for predicting articulatory features from surface electromyography (EMG) signals during speech production. The proposed model integrates convolutional layers and a Transformer block, followed by separate predictors for articulatory features. Our approach achieves a high prediction correlation of approximately 0.9 for most articulatory features. Furthermore, we demonstrate that these predicted articulatory features can be decoded into intelligible speech waveforms. To our knowledge, this is the first method to decode speech waveforms from surface EMG via articulatory features, offering a novel approach to EMG-based speech synthesis. Additionally, we analyze the relationship between EMG electrode placement and articulatory feature predictability, providing knowledge-driven insights for optimizing EMG electrode configurations. The source code and decoded speech samples are publicly available.

Laura Moradbakhti, Dorian Peters, Jennifer K. Quint et al.

Asthma-related deaths in the UK are the highest in Europe, and only 30% of patients access basic care. There is a need for alternative approaches to reaching people with asthma in order to provide health education, self-management support and bridges to care. Automated conversational agents (specifically, mobile chatbots) present opportunities for providing alternative and individually tailored access to health education, self-management support and risk self-assessment. But would patients engage with a chatbot, and what factors influence engagement? We present results from a patient survey (N=1257) devised by a team of asthma clinicians, patients, and technology developers, conducted to identify optimal factors for efficacy, value and engagement for a chatbot. Results indicate that most adults with asthma (53%) are interested in using a chatbot and the patients most likely to do so are those who believe their asthma is more serious and who are less confident about self-management. Results also indicate enthusiasm for 24/7 access, personalisation, and for WhatsApp as the preferred access method (compared to app, voice assistant, SMS or website). Obstacles to uptake include security/privacy concerns and skepticism of technological capabilities. We present detailed findings and consolidate these into 7 recommendations for developers for optimising efficacy of chatbot-based health support.

Cuno Sankey-Olsen, Rasmus Hvass Olesen, Tobias Oliver Eberhard et al.

Chronic Obstructive Pulmonary Disease (COPD) is a serious and debilitating disease affecting millions around the world. Its early detection using non-invasive means could enable preventive interventions that improve quality of life and patient outcomes, with speech recently shown to be a valuable biomarker. Yet, its validity across different linguistic groups remains to be seen. To that end, audio data were collected from 96 Danish participants conducting three speech tasks (reading, coughing, sustained vowels). Half of the participants were diagnosed with different levels of COPD and the other half formed a healthy control group. Subsequently, we investigated different baseline models using openSMILE features and learnt x-vector embeddings. We obtained a best accuracy of 67% using openSMILE features and logistic regression. Our findings support the potential of speech-based analysis as a non-invasive, remote, and scalable screening tool as part of future COPD healthcare solutions.

David Funosas, Elodie Massol, Yves Bas et al.

Currently available tools for the automated acoustic recognition of European insects in natural soundscapes are limited in scope. Large and ecologically heterogeneous acoustic datasets are currently needed for these algorithms to cross-contextually recognize the subtle and complex acoustic signatures produced by each species, thus making the availability of such datasets a key requisite for their development. Here we present ECOSoundSet (European Cicadidae and Orthoptera Sound dataSet), a dataset containing 10,653 recordings of 200 orthopteran and 24 cicada species (217 and 26 respective taxa when including subspecies) present in North, Central, and temperate Western Europe (Andorra, Belgium, Denmark, mainland France and Corsica, Germany, Ireland, Luxembourg, Monaco, Netherlands, United Kingdom, Switzerland), collected partly through targeted fieldwork in South France and Catalonia and partly through contributions from various European entomologists. The dataset is composed of a combination of coarsely labeled recordings, for which we can only infer the presence, at some point, of their target species (weak labeling), and finely annotated recordings, for which we know the specific time and frequency range of each insect sound present in the recording (strong labeling). We also provide a train/validation/test split of the strongly labeled recordings, with respective approximate proportions of 0.8, 0.1 and 0.1, in order to facilitate their incorporation in the training and evaluation of deep learning algorithms. This dataset could serve as a meaningful complement to recordings already available online for the training of deep learning algorithms for the acoustic classification of orthopterans and cicadas in North, Central, and temperate Western Europe.

Shahin Amiriparian, Lukas Christ, Alexander Kathan et al.

The Multimodal Sentiment Analysis Challenge (MuSe) 2024 addresses two contemporary multimodal affect and sentiment analysis problems: In the Social Perception Sub-Challenge (MuSe-Perception), participants will predict 16 different social attributes of individuals such as assertiveness, dominance, likability, and sincerity based on the provided audio-visual data. The Cross-Cultural Humor Detection Sub-Challenge (MuSe-Humor) dataset expands upon the Passau Spontaneous Football Coach Humor (Passau-SFCH) dataset, focusing on the detection of spontaneous humor in a cross-lingual and cross-cultural setting. The main objective of MuSe 2024 is to unite a broad audience from various research domains, including multimodal sentiment analysis, audio-visual affective computing, continuous signal processing, and natural language processing. By fostering collaboration and exchange among experts in these fields, the MuSe 2024 endeavors to advance the understanding and application of sentiment analysis and affective computing across multiple modalities. This baseline paper provides details on each sub-challenge and its corresponding dataset, extracted features from each data modality, and discusses challenge baselines. For our baseline system, we make use of a range of Transformers and expert-designed features and train Gated Recurrent Unit (GRU)-Recurrent Neural Network (RNN) models on them, resulting in a competitive baseline system. On the unseen test datasets of the respective sub-challenges, it achieves a mean Pearson's Correlation Coefficient ($ρ$) of 0.3573 for MuSe-Perception and an Area Under the Curve (AUC) value of 0.8682 for MuSe-Humor.

Andreas Triantafyllopoulos, Björn Schuller

The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size-fits-all' approach for predicting emotion. Moreover, standard evaluation practices measure performance also on the population level, thus failing to characterise how models work across different speakers. In the present contribution, we present a new method for capitalising on individual differences to adapt an SER model to each new speaker using a minimal set of enrolment utterances. In addition, we present novel evaluation schemes for measuring fairness across different speakers. Our findings show that aggregated evaluation metrics may obfuscate fairness issues on the individual-level, which are uncovered by our evaluation, and that our proposed method can improve performance both in aggregated and disaggregated terms.

Andreas Triantafyllopoulos, Anton Batliner, Simon Rampp et al.

We revisit the INTERSPEECH 2009 Emotion Challenge -- the first ever speech emotion recognition (SER) challenge -- and evaluate a series of deep learning models that are representative of the major advances in SER research in the time since then. We start by training each model using a fixed set of hyperparameters, and further fine-tune the best-performing models of that initial setup with a grid search. Results are always reported on the official test set with a separate validation set only used for early stopping. Most models score below or close to the official baseline, while they marginally outperform the original challenge winners after hyperparameter tuning. Our work illustrates that, despite recent progress, FAU-AIBO remains a very challenging benchmark. An interesting corollary is that newer methods do not consistently outperform older ones, showing that progress towards `solving' SER is not necessarily monotonic.

Andreas Triantafyllopoulos, Anton Batliner, Wolfgang Mayr et al.

Chronic obstructive pulmonary disease (COPD) is a serious inflammatory lung disease affecting millions of people around the world. Due to an obstructed airflow from the lungs, it also becomes manifest in patients' vocal behaviour. Of particular importance is the detection of an exacerbation episode, which marks an acute phase and often requires hospitalisation and treatment. Previous work has shown that it is possible to distinguish between a pre- and a post-treatment state using automatic analysis of read speech. In this contribution, we examine whether sustained vowels can provide a complementary lens for telling apart these two states. Using a cohort of 50 patients, we show that the inclusion of sustained vowels can improve performance to up to 79\% unweighted average recall, from a 71\% baseline using read speech. We further identify and interpret the most important acoustic features that characterise the manifestation of COPD in sustained vowels.

Yong Wang, Cheng Lu, Hailun Lian et al.

Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional information is distributed across different scales of speech features, e.\,g., word, phrase, and utterance. Drawing above inspiration, this paper presents a hierarchical speech Transformer with shifted windows to aggregate multi-scale emotion features for speech emotion recognition (SER), called Speech Swin-Transformer. Specifically, we first divide the speech spectrogram into segment-level patches in the time domain, composed of multiple frame patches. These segment-level patches are then encoded using a stack of Swin blocks, in which a local window Transformer is utilized to explore local inter-frame emotional information across frame patches of each segment patch. After that, we also design a shifted window Transformer to compensate for patch correlations near the boundaries of segment patches. Finally, we employ a patch merging operation to aggregate segment-level emotional features for hierarchical speech representation by expanding the receptive field of Transformer from frame-level to segment-level. Experimental results demonstrate that our proposed Speech Swin-Transformer outperforms the state-of-the-art methods.

Cheng Lu, Yuan Zong, Hailun Lian et al.

In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers. Consequently, when the trained model is confronted with data from new speakers, its performance tends to degrade. To address the issue, we propose a Dynamic Joint Distribution Adaptation (DJDA) method under the framework of multi-source domain adaptation. DJDA firstly utilizes joint distribution adaptation (JDA), involving marginal distribution adaptation (MDA) and conditional distribution adaptation (CDA), to more precisely measure the multi-domain distribution shifts caused by different speakers. This helps eliminate speaker bias in emotion features, allowing for learning discriminative and speaker-invariant speech emotion features from coarse-level to fine-level. Furthermore, we quantify the adaptation contributions of MDA and CDA within JDA by using a dynamic balance factor based on $\mathcal{A}$-Distance, promoting to effectively handle the unknown distributions encountered in data from new speakers. Experimental results demonstrate the superior performance of our DJDA as compared to other state-of-the-art (SOTA) methods.

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Speech Emotion Recognition (SER) is a critical enabler of emotion-aware communication in human-computer interactions. Recent advancements in Deep Learning (DL) have substantially enhanced the performance of SER models through increased model complexity. However, designing optimal DL architectures requires prior experience and experimental evaluations. Encouragingly, Neural Architecture Search (NAS) offers a promising avenue to determine an optimal DL model automatically. In particular, Differentiable Architecture Search (DARTS) is an efficient method of using NAS to search for optimised models. This paper proposes a DARTS-optimised joint CNN and LSTM architecture, to improve SER performance, where the literature informs the selection of CNN and LSTM coupling to offer improved performance. While DARTS has previously been applied to CNN and LSTM combinations, our approach introduces a novel mechanism, particularly in selecting CNN operations using DARTS. In contrast to previous studies, we refrain from imposing constraints on the order of the layers for the CNN within the DARTS cell; instead, we allow DARTS to determine the optimal layer order autonomously. Experimenting with the IEMOCAP and MSP-IMPROV datasets, we demonstrate that our proposed methodology achieves significantly higher SER accuracy than hand-engineering the CNN-LSTM configuration. It also outperforms the best-reported SER results achieved using DARTS on CNN-LSTM.

Alice Baird, Panagiotis Tzirakis, Gauthier Gidel et al.

This is the Proceedings of the ICML Expressive Vocalization (ExVo) Competition. The ExVo competition focuses on understanding and generating vocal bursts: laughs, gasps, cries, and other non-verbal vocalizations that are central to emotional expression and communication. ExVo 2022, included three competition tracks using a large-scale dataset of 59,201 vocalizations from 1,702 speakers. The first, ExVo-MultiTask, requires participants to train a multi-task model to recognize expressed emotions and demographic traits from vocal bursts. The second, ExVo-Generate, requires participants to train a generative model that produces vocal bursts conveying ten different emotions. The third, ExVo-FewShot, requires participants to leverage few-shot learning incorporating speaker identity to train a model for the recognition of 10 emotions conveyed by vocal bursts.

Sandra Ottl, Shahin Amiriparian, Maurice Gerczuk et al.

In this paper, human semen samples from the visem dataset collected by the Simula Research Laboratory are automatically assessed with machine learning methods for their quality in respect to sperm motility. Several regression models are trained to automatically predict the percentage (0 to 100) of progressive, non-progressive, and immotile spermatozoa in a given sample. The video samples are adopted for three different feature extraction methods, in particular custom movement statistics, displacement features, and motility specific statistics have been utilised. Furthermore, four machine learning models, including linear Support Vector Regressor (SVR), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN), have been trained on the extracted features for the task of automatic motility prediction. Best results for predicting motility are achieved by using the Crocker-Grier algorithm to track sperm cells in an unsupervised way and extracting individual mean squared displacement features for each detected track. These features are then aggregated into a histogram representation applying a Bag-of-Words approach. Finally, a linear SVR is trained on this feature representation. Compared to the best submission of the Medico Multimedia for Medicine challenge, which used the same dataset and splits, the Mean Absolute Error (MAE) could be reduced from 8.83 to 7.31. For the sake of reproducibility, we provide the source code for our experiments on GitHub.

Lukas Stappen, Alice Baird, Michelle Lienhart et al.

Portraying emotion and trustworthiness is known to increase the appeal of video content. However, the causal relationship between these signals and online user engagement is not well understood. This limited understanding is partly due to a scarcity in emotionally annotated data and the varied modalities which express user engagement online. In this contribution, we utilise a large dataset of YouTube review videos which includes ca. 600 hours of dimensional arousal, valence and trustworthiness annotations. We investigate features extracted from these signals against various user engagement indicators including views, like/dislike ratio, as well as the sentiment of comments. In doing so, we identify the positive and negative influences which single features have, as well as interpretable patterns in each dimension which relate to user engagement. Our results demonstrate that smaller boundary ranges and fluctuations for arousal lead to an increase in user engagement. Furthermore, the extracted time-series features reveal significant (p<0.05) correlations for each dimension, such as, count below signal mean (arousal), number of peaks (valence), and absolute energy (trustworthiness). From this, an effective combination of features is outlined for approaches aiming to automatically predict several user engagement indicators. In a user engagement prediction paradigm we compare all features against semi-automatic (cross-task), and automatic (task-specific) feature selection methods. These selected feature sets appear to outperform the usage of all features, e.g., using all features achieves 1.55 likes per day (Lp/d) mean absolute error from valence; this improves through semi-automatic and automatic selection to 1.33 and 1.23 Lp/d, respectively (data mean 9.72 Lp/d with a std. 28.75 Lp/d).

Shuo Liu, Jing Han, Estela Laporta Puyal et al.

This study investigates the potential of deep learning methods to identify individuals with suspected COVID-19 infection using remotely collected heart-rate data. The study utilises data from the ongoing EU IMI RADAR-CNS research project that is investigating the feasibility of wearable devices and smart phones to monitor individuals with multiple sclerosis (MS), depression or epilepsy. Aspart of the project protocol, heart-rate data was collected from participants using a Fitbit wristband. The presence of COVID-19 in the cohort in this work was either confirmed through a positive swab test, or inferred through the self-reporting of a combination of symptoms including fever, respiratory symptoms, loss of smell or taste, tiredness and gastrointestinal symptoms. Experimental results indicate that our proposed contrastive convolutional auto-encoder (contrastive CAE), i. e., a combined architecture of an auto-encoder and contrastive loss, outperforms a conventional convolutional neural network (CNN), as well as a convolutional auto-encoder (CAE) without using contrastive loss. Our final contrastive CAE achieves 95.3% unweighted average recall, 86.4% precision, anF1 measure of 88.2%, a sensitivity of 100% and a specificity of 90.6% on a testset of 19 participants with MS who reported symptoms of COVID-19. Each of these participants was paired with a participant with MS with no COVID-19 symptoms.

Decky Aspandi, Federico Sukno, Björn Schuller et al.

Affective Computing has recently attracted the attention of the research community, due to its numerous applications in diverse areas. In this context, the emergence of video-based data allows to enrich the widely used spatial features with the inclusion of temporal information. However, such spatio-temporal modelling often results in very high-dimensional feature spaces and large volumes of data, making training difficult and time consuming. This paper addresses these shortcomings by proposing a novel model that efficiently extracts both spatial and temporal features of the data by means of its enhanced temporal modelling based on latent features. Our proposed model consists of three major networks, coined Generator, Discriminator, and Combiner, which are trained in an adversarial setting combined with curriculum learning to enable our adaptive attention modules. In our experiments, we show the effectiveness of our approach by reporting our competitive results on both the AFEW-VA and SEWA datasets, suggesting that temporal modelling improves the affect estimates both in qualitative and quantitative terms. Furthermore, we find that the inclusion of attention mechanisms leads to the highest accuracy improvements, as its weights seem to correlate well with the appearance of facial movements, both in terms of temporal localisation and intensity. Finally, we observe the sequence length of around 160\,ms to be the optimum one for temporal modelling, which is consistent with other relevant findings utilising similar lengths.

Lukas Stappen, Alice Baird, Lea Schumann et al.

Truly real-life data presents a strong, but exciting challenge for sentiment and emotion research. The high variety of possible `in-the-wild' properties makes large datasets such as these indispensable with respect to building robust machine learning models. A sufficient quantity of data covering a deep variety in the challenges of each modality to force the exploratory analysis of the interplay of all modalities has not yet been made available in this context. In this contribution, we present MuSe-CaR, a first of its kind multimodal dataset. The data is publicly available as it recently served as the testing bed for the 1st Multimodal Sentiment Analysis Challenge, and focused on the tasks of emotion, emotion-target engagement, and trustworthiness recognition by means of comprehensively integrating the audio-visual and language modalities. Furthermore, we give a thorough overview of the dataset in terms of collection and annotation, including annotation tiers not used in this year's MuSe 2020. In addition, for one of the sub-challenges - predicting the level of trustworthiness - no participant outperformed the baseline model, and so we propose a simple, but highly efficient Multi-Head-Attention network that exceeds using multimodal fusion the baseline by around 0.2 CCC (almost 50 % improvement).

Ognjen Rudovic, Nicolas Tobis, Sebastian Kaltwang et al.

Standard machine learning approaches require centralizing the users' data in one computer or a shared database, which raises data privacy and confidentiality concerns. Therefore, limiting central access is important, especially in healthcare settings, where data regulations are strict. A potential approach to tackling this is Federated Learning (FL), which enables multiple parties to collaboratively learn a shared prediction model by using parameters of locally trained models while keeping raw training data locally. In the context of AI-assisted pain-monitoring, we wish to enable confidentiality-preserving and unobtrusive pain estimation for long-term pain-monitoring and reduce the burden on the nursing staff who perform frequent routine check-ups. To this end, we propose a novel Personalized Federated Deep Learning (PFDL) approach for pain estimation from face images. PFDL performs collaborative training of a deep model, implemented using a lightweight CNN architecture, across different clients (i.e., subjects) without sharing their face images. Instead of sharing all parameters of the model, as in standard FL, PFDL retains the last layer locally (used to personalize the pain estimates). This (i) adds another layer of data confidentiality, making it difficult for an adversary to infer pain levels of the target subject, while (ii) personalizing the pain estimation to each subject through local parameter tuning. We show using a publicly available dataset of face videos of pain (UNBC-McMaster Shoulder Pain Database), that PFDL performs comparably or better than the standard centralized and FL algorithms, while further enhancing data privacy. This, has the potential to improve traditional pain monitoring by making it more secure, computationally efficient, and scalable to a large number of individuals (e.g., for in-home pain monitoring), providing timely and unobtrusive pain measurement.

Gauri Deshpande, Björn Schuller

Recently, there has been an increased attention towards innovating, enhancing, building, and deploying applications of speech signal processing for providing assistance and relief to human mankind from the Coronavirus (COVID-19) pandemic. Many AI with speech initiatives are taken to combat with the present situation and also to create a safe and secure environment for the future. This paper summarises all these efforts taken by the re-search community towards helping the individuals and the society in the fight against COVID-19 over the past 3-4 months using speech signal processing. We also summarise the deep techniques used in this direction to come up with capable solutions in a short span of time. This paper further gives an overview of the contributions from non-speech modalities that may complement or serve as inspiration for audio and speech analysis. In addition, we discuss our observations with respect to solution usability, challenges, and the significant technology achievements.

Lukas Stappen, Fabian Brunn, Björn Schuller

Detecting hate speech, especially in low-resource languages, is a non-trivial challenge. To tackle this, we developed a tailored architecture based on frozen, pre-trained Transformers to examine cross-lingual zero-shot and few-shot learning, in addition to uni-lingual learning, on the HatEval challenge data set. With our novel attention-based classification block AXEL, we demonstrate highly competitive results on the English and Spanish subsets. We also re-sample the English subset, enabling additional, meaningful comparisons in the future.

Kazi Nazmul Haque, Rajib Rana, John H. L. Hansen et al.

Recent improvements in Generative Adversarial Neural Networks (GANs) have shown their ability to generate higher quality samples as well as to learn good representations for transfer learning. Most of the representation learning methods based on GANs learn representations ignoring their post-use scenario, which can lead to increased generalisation ability. However, the model can become redundant if it is intended for a specific task. For example, assume we have a vast unlabelled audio dataset, and we want to learn a representation from this dataset so that it can be used to improve the emotion recognition performance of a small labelled audio dataset. During the representation learning training, if the model does not know the post emotion recognition task, it can completely ignore emotion-related characteristics in the learnt representation. This is a fundamental challenge for any unsupervised representation learning model. In this paper, we aim to address this challenge by proposing a novel GAN framework: Guided Generative Neural Network (GGAN), which guides a GAN to focus on learning desired representations and generating superior quality samples for audio data leveraging fewer labelled samples. Experimental results show that using a very small amount of labelled data as guidance, a GGAN learns significantly better representations.

Decky Aspandi, Adria Mallol-Ragolta, Björn Schuller et al.

There is a growing interest in affective computing research nowadays given its crucial role in bridging humans with computers. This progress has been recently accelerated due to the emergence of bigger data. One recent advance in this field is the use of adversarial learning to improve model learning through augmented samples. However, the use of latent features, which is feasible through adversarial learning, is not largely explored, yet. This technique may also improve the performance of affective models, as analogously demonstrated in related fields, such as computer vision. To expand this analysis, in this work, we explore the use of latent features through our proposed adversarial-based networks for valence and arousal recognition in the wild. Specifically, our models operate by aggregating several modalities to our discriminator, which is further conditioned to the extracted latent features by the generator. Our experiments on the recently released SEWA dataset suggest the progressive improvements of our results. Finally, we show our competitive results on the Affective Behavior Analysis in-the-Wild (ABAW) challenge dataset

Ali Girayhan Özbay, Arash Hamzehloo, Sylvain Laizet et al.

The Poisson equation is commonly encountered in engineering, for instance in computational fluid dynamics (CFD) where it is needed to compute corrections to the pressure field to ensure the incompressibility of the velocity field. In the present work, we propose a novel fully convolutional neural network (CNN) architecture to infer the solution of the Poisson equation on a 2D Cartesian grid with different resolutions given the right hand side term, arbitrary boundary conditions and grid parameters. It provides unprecedented versatility for a CNN approach dealing with partial differential equations. The boundary conditions are handled using a novel approach by decomposing the original Poisson problem into a homogeneous Poisson problem plus four inhomogeneous Laplace sub-problems. The model is trained using a novel loss function approximating the continuous $L^p$ norm between the prediction and the target. Even when predicting on grids denser than previously encountered, our model demonstrates encouraging capacity to reproduce the correct solution profile. The proposed model, which outperforms well-known neural network models, can be included in a CFD solver to help with solving the Poisson equation. Analytical test cases indicate that our CNN architecture is capable of predicting the correct solution of a Poisson problem with mean percentage errors below 10%, an improvement by comparison to the first step of conventional iterative methods. Predictions from our model, used as the initial guess to iterative algorithms like Multigrid, can reduce the RMS error after a single iteration by more than 90% compared to a zero initial guess.

Anton Batliner, Stefan Steidl, Florian Eyben et al.

In this article, we study laughter found in child-robot interaction where it had not been prompted intentionally. Different types of laughter and speech-laugh are annotated and processed. In a descriptive part, we report on the position of laughter and speech-laugh in syntax and dialogue structure, and on communicative functions. In a second part, we report on automatic classification performance and on acoustic characteristics, based on extensive feature selection procedures.

Jing Han, Zixing Zhang, Zhao Ren et al.

Despite remarkable advances in emotion recognition, they are severely restrained from either the essentially limited property of the employed single modality, or the synchronous presence of all involved multiple modalities. Motivated by this, we propose a novel crossmodal emotion embedding framework called EmoBed, which aims to leverage the knowledge from other auxiliary modalities to improve the performance of an emotion recognition system at hand. The framework generally includes two main learning components, i. e., joint multimodal training and crossmodal training. Both of them tend to explore the underlying semantic emotion information but with a shared recognition network or with a shared emotion embedding space, respectively. In doing this, the enhanced system trained with this approach can efficiently make use of the complementary information from other modalities. Nevertheless, the presence of these auxiliary modalities is not demanded during inference. To empirically investigate the effectiveness and robustness of the proposed framework, we perform extensive experiments on the two benchmark databases RECOLA and OMG-Emotion for the tasks of dimensional emotion regression and categorical emotion classification, respectively. The obtained results show that the proposed framework significantly outperforms related baselines in monomodal inference, and are also competitive or superior to the recently reported systems, which emphasises the importance of the proposed crossmodal learning for emotion recognition.

Fabien Ringeval, Björn Schuller, Michel Valstar et al.

The Audio/Visual Emotion Challenge and Workshop (AVEC 2019) "State-of-Mind, Detecting Depression with AI, and Cross-cultural Affect Recognition" is the ninth competition event aimed at the comparison of multimedia processing and machine learning methods for automatic audiovisual health and emotion analysis, with all participants competing strictly under the same conditions. The goal of the Challenge is to provide a common benchmark test set for multimodal information processing and to bring together the health and emotion recognition communities, as well as the audiovisual processing communities, to compare the relative merits of various approaches to health and emotion recognition from real-life data. This paper presents the major novelties introduced this year, the challenge guidelines, the data used, and the performance of the baseline systems on the three proposed tasks: state-of-mind recognition, depression assessment with AI, and cross-cultural affect sensing, respectively.

Shuo Liu, Gil Keren, Björn Schuller

We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the challenging VoxCeleb dataset, the proposed model yields 4.79dB signal-to-distortion ratio, 8.44dB signal-to-artifacts ratio and 7.11dB signal-to-interference ratio.

Panagiotis Tzirakis, Athanasios Papaioannou, Alexander Lattas et al.

Synthesising 3D facial motion from speech is a crucial problem manifesting in a multitude of applications such as computer games and movies. Recently proposed methods tackle this problem in controlled conditions of speech. In this paper, we introduce the first methodology for 3D facial motion synthesis from speech captured in arbitrary recording conditions ("in-the-wild") and independent of the speaker. For our purposes, we captured 4D sequences of people uttering 500 words, contained in the Lip Reading Words (LRW) a publicly available large-scale in-the-wild dataset, and built a set of 3D blendshapes appropriate for speech. We correlate the 3D shape parameters of the speech blendshapes to the LRW audio samples by means of a novel time-warping technique, named Deep Canonical Attentional Warping (DCAW), that can simultaneously learn hierarchical non-linear representations and a warping path in an end-to-end manner. We thoroughly evaluate our proposed methods, and show the ability of a deep learning model to synthesise 3D facial motion in handling different speakers and continuous speech signals in uncontrolled conditions.

Thomas Wiest, Nicholas Cummins, Alice Baird et al.

Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data resources. One less-explored application of GANs is the synthesis of speech and audio samples. Herein, we propose a set of extensions to the WaveGAN paradigm, a recently proposed approach for sound generation using GANs. The aim of these extensions - preprocessing, Audio-to-Audio generation, skip connections and progressive structures - is to improve the human likeness of synthetic speech samples. Scores from listening tests with 30 volunteers demonstrated a moderate improvement (Cohen's d coefficient of 0.65) in human likeness using the proposed extensions compared to the original WaveGAN approach.