Thierry Dutoit

Antoine Maiorca, Youngwoo Yoon, Thierry Dutoit

Evaluating the Quality of a Synthesized Motion with the Fréchet Motion Distance

Victor Delvigne, Hazem Wannous, Jean-Philippe Vandeborre et al.

For many years now, understanding the brain mechanism has been a great research subject in many different fields. Brain signal processing and especially electroencephalogram (EEG) has recently known a growing interest both in academia and industry. One of the main examples is the increasing number of Brain-Computer Interfaces (BCI) aiming to link brains and computers. In this paper, we present a novel framework allowing us to retrieve the attention state, i.e degree of attention given to a specific task, from EEG signals. While previous methods often consider the spatial relationship in EEG through electrodes and process them in recurrent or convolutional based architecture, we propose here to also exploit the spatial and temporal information with a transformer-based network that has already shown its supremacy in many machine-learning (ML) related studies, e.g. machine translation. In addition to this novel architecture, an extensive study on the feature extraction methods, frequential bands and temporal windows length has also been carried out. The proposed network has been trained and validated on two public datasets and achieves higher results compared to state-of-the-art models. As well as proposing better results, the framework could be used in real applications, e.g. Attention Deficit Hyperactivity Disorder (ADHD) symptoms or vigilance during a driving assessment.

Gwendal Le Vaillant, Thierry Dutoit

Sound synthesizers are widespread in modern music production but they increasingly require expert skills to be mastered. This work focuses on interpolation between presets, i.e., sets of values of all sound synthesis parameters, to enable the intuitive creation of new sounds from existing ones. We introduce a bimodal auto-encoder neural network, which simultaneously processes presets using multi-head attention blocks, and audio using convolutions. This model has been tested on a popular frequency modulation synthesizer with more than one hundred parameters. Experiments have compared the model to related architectures and methods, and have demonstrated that it performs smoother interpolations. After training, the proposed model can be integrated into commercial synthesizers for live interpolation or sound design tasks.

Omar Seddati, Stéphane Dupont, Saïd Mahmoudi et al.

Sketch-based image retrieval (SBIR) is the task of retrieving natural images (photos) that match the semantics and the spatial configuration of hand-drawn sketch queries. The universality of sketches extends the scope of possible applications and increases the demand for efficient SBIR solutions. In this paper, we study classic triplet-based SBIR solutions and show that a persistent invariance to horizontal flip (even after model finetuning) is harming performance. To overcome this limitation, we propose several approaches and evaluate in depth each of them to check their effectiveness. Our main contributions are twofold: We propose and evaluate several intuitive modifications to build SBIR solutions with better flip equivariance. We show that vision transformers are more suited for the SBIR task, and that they outperform CNNs with a large margin. We carried out numerous experiments and introduce the first models to outperform human performance on a large-scale SBIR benchmark (Sketchy). Our best model achieves a recall of 62.25% (at k = 1) on the sketchy benchmark compared to previous state-of-the-art methods 46.2%.

Hugo Bohy, Ahmad Hammoudeh, Antoine Maiorca et al.

The development of virtual agents has enabled human-avatar interactions to become increasingly rich and varied. Moreover, an expressive virtual agent i.e. that mimics the natural expression of emotions, enhances social interaction between a user (human) and an agent (intelligent machine). The set of non-verbal behaviors of a virtual character is, therefore, an important component in the context of human-machine interaction. Laughter is not just an audio signal, but an intrinsic relationship of multimodal non-verbal communication, in addition to audio, it includes facial expressions and body movements. Motion analysis often relies on a relevant motion capture dataset, but the main issue is that the acquisition of such a dataset is expensive and time-consuming. This work studies the relationship between laughter and body movements in dyadic conversations. The body movements were extracted from videos using deep learning based pose estimator model. We found that, in the explored NDC-ME dataset, a single statistical feature (i.e, the maximum value, or the maximum of Fourier transform) of a joint movement weakly correlates with laughter intensity by 30%. However, we did not find a direct correlation between audio features and body movements. We discuss about the challenges to use such dataset for the audio-driven co-laughter motion synthesis task.

Nicolas Boizard, Kevin El Haddad, Thierry Ravet et al.

Stereo vision is essential for many applications. Currently, the synchronization of the streams coming from two cameras is done using mostly hardware. A software-based synchronization method would reduce the cost, weight and size of the entire system and allow for more flexibility when building such systems. With this goal in mind, we present here a comparison of different deep learning-based systems and prove that some are efficient and generalizable enough for such a task. This study paves the way to a production ready software-based video synchronization system.

Victor Delvigne, Antoine Facchini, Hazem Wannous et al.

Among the different modalities to assess emotion, electroencephalogram (EEG), representing the electrical brain activity, achieved motivating results over the last decade. Emotion estimation from EEG could help in the diagnosis or rehabilitation of certain diseases. In this paper, we propose a dual model considering two different representations of EEG feature maps: 1) a sequential based representation of EEG band power, 2) an image-based representation of the feature vectors. We also propose an innovative method to combine the information based on a saliency analysis of the image-based model to promote joint learning of both model parts. The model has been evaluated on four publicly available datasets: SEED-IV, SEED, DEAP and MPED. The achieved results outperform results from state-of-the-art approaches for three of the proposed datasets with a lower standard deviation that reflects higher stability. For sake of reproducibility, the codes and models proposed in this paper are available at https://github.com/VDelv/Emotion-EEG.

Noé Tits, Prernna Bhatnagar, Thierry Dutoit

In this paper, we present a novel approach for text independent phone-to-audio alignment based on phoneme recognition, representation learning and knowledge transfer. Our method leverages a self-supervised model (wav2vec2) fine-tuned for phoneme recognition using a Connectionist Temporal Classification (CTC) loss, a dimension reduction model and a frame-level phoneme classifier trained thanks to forced-alignment labels (using Montreal Forced Aligner) to produce multi-lingual phonetic representations, thus requiring minimal additional training. We evaluate our model using synthetic native data from the TIMIT dataset and the SCRIBE dataset for American and British English, respectively. Our proposed model outperforms the state-of-the-art (charsiu) in statistical metrics and has applications in language learning and speech processing systems. We leave experiments on other languages for future work but the design of the system makes it easily adaptable to other languages.

Omar Seddati, Nathan Hubens, Stéphane Dupont et al.

Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have already proposed several well-performing solutions for this task, but most focus on enhancing embedding through different approaches such as triplet loss, quadruplet loss, adding data augmentation, and using edge extraction. In this work, we tackle the problem from various angles. We start by examining the training data quality and show some of its limitations. Then, we introduce a Relative Triplet Loss (RTL), an adapted triplet loss to overcome those limitations through loss weighting based on anchors similarity. Through a series of experiments, we demonstrate that replacing a triplet loss with RTL outperforms previous state-of-the-art without the need for any data augmentation. In addition, we demonstrate why batch normalization is more suited for SBIR embeddings than l2-normalization and show that it improves significantly the performance of our models. We further investigate the capacity of models required for the photo and sketch domains and demonstrate that the photo encoder requires a higher capacity than the sketch encoder, which validates the hypothesis formulated in [34]. Then, we propose a straightforward approach to train small models, such as ShuffleNetv2 [22] efficiently with a marginal loss of accuracy through knowledge distillation. The same approach used with larger models enabled us to outperform previous state-of-the-art results and achieve a recall of 62.38% at k = 1 on The Sketchy Database [30].

Antoine Maiorca, Nathan Hubens, Sohaib Laraba et al.

In the past few years, neural character animation has emerged and offered an automatic method for animating virtual characters. Their motion is synthesized by a neural network. Controlling this movement in real time with a user-defined control signal is also an important task in video games for example. Solutions based on fully-connected layers (MLPs) and Mixture-of-Experts (MoE) have given impressive results in generating and controlling various movements with close-range interactions between the environment and the virtual character. However, a major shortcoming of fully-connected layers is their computational and memory cost which may lead to sub-optimized solution. In this work, we apply pruning algorithms to compress an MLP- MoE neural network in the context of interactive character animation, which reduces its number of parameters and accelerates its computation time with a trade-off between this acceleration and the synthesized motion quality. This work demonstrates that, with the same number of experts and parameters, the pruned model produces less motion artifacts than the dense model and the learned high-level motion features are similar for both

Victor Delvigne, Noé Tits, Luca La Fisca et al.

Visual attention estimation is an active field of research at the crossroads of different disciplines: computer vision, artificial intelligence and medicine. One of the most common approaches to estimate a saliency map representing attention is based on the observed images. In this paper, we show that visual attention can be retrieved from EEG acquisition. The results are comparable to traditional predictions from observed images, which is of great interest. For this purpose, a set of signals has been recorded and different models have been developed to study the relationship between visual attention and brain activity. The results are encouraging and comparable with other approaches estimating attention with other modalities. The codes and dataset considered in this paper have been made available at \url{https://figshare.com/s/3e353bd1c621962888ad} to promote research in the field.

Noé Tits, Kevin El Haddad, Thierry Dutoit

In this paper, we study the controllability of an Expressive TTS system trained on a dataset for a continuous control. The dataset is the Blizzard 2013 dataset based on audiobooks read by a female speaker containing a great variability in styles and expressiveness. Controllability is evaluated with both an objective and a subjective experiment. The objective assessment is based on a measure of correlation between acoustic features and the dimensions of the latent space representing expressiveness. The subjective assessment is based on a perceptual experiment in which users are shown an interface for Controllable Expressive TTS and asked to retrieve a synthetic utterance whose expressiveness subjectively corresponds to that a reference utterance.

Thomas Drugman, Thomas Dubuisson, Thierry Dutoit

This paper addresses the problem of automatic detection of voice pathologies directly from the speech signal. For this, we investigate the use of the glottal source estimation as a means to detect voice disorders. Three sets of features are proposed, depending on whether they are related to the speech or the glottal signal, or to prosody. The relevancy of these features is assessed through mutual information-based measures. This allows an intuitive interpretation in terms of discrimation power and redundancy between the features, independently of any subsequent classifier. It is discussed which characteristics are interestingly informative or complementary for detecting voice pathologies.

Thomas Drugman, Baris Bozkurt, Thierry Dutoit

Homomorphic analysis is a well-known method for the separation of non-linearly combined signals. More particularly, the use of complex cepstrum for source-tract deconvolution has been discussed in various articles. However there exists no study which proposes a glottal flow estimation methodology based on cepstrum and reports effective results. In this paper, we show that complex cepstrum can be effectively used for glottal flow estimation by separating the causal and anticausal components of a windowed speech signal as done by the Zeros of the Z-Transform (ZZT) decomposition. Based on exactly the same principles presented for ZZT decomposition, windowing should be applied such that the windowed speech signals exhibit mixed-phase characteristics which conform the speech production model that the anticausal component is mainly due to the glottal flow open phase. The advantage of the complex cepstrum-based approach compared to the ZZT decomposition is its much higher speed.

Noé Tits, Kevin El Haddad, Thierry Dutoit

As part of the Human-Computer Interaction field, Expressive speech synthesis is a very rich domain as it requires knowledge in areas such as machine learning, signal processing, sociology, psychology. In this Chapter, we will focus mostly on the technical side. From the recording of expressive speech to its modeling, the reader will have an overview of the main paradigms used in this field, through some of the most prominent systems and methods. We explain how speech can be represented and encoded with audio features. We present a history of the main methods of Text-to-Speech synthesis: concatenative, parametric and statistical parametric speech synthesis. Finally, we focus on the last one, with the last techniques modeling Text-to-Speech synthesis as a sequence-to-sequence problem. This enables the use of Deep Learning blocks such as Convolutional and Recurrent Neural Networks as well as Attention Mechanism. The last part of the Chapter intends to assemble the different aspects of the theory and summarize the concepts.

Noé Tits, Fengna Wang, Kevin El Haddad et al.

The field of Text-to-Speech has experienced huge improvements last years benefiting from deep learning techniques. Producing realistic speech becomes possible now. As a consequence, the research on the control of the expressiveness, allowing to generate speech in different styles or manners, has attracted increasing attention lately. Systems able to control style have been developed and show impressive results. However the control parameters often consist of latent variables and remain complex to interpret. In this paper, we analyze and compare different latent spaces and obtain an interpretation of their influence on expressive speech. This will enable the possibility to build controllable speech synthesis systems with an understandable behaviour.

Nicolas Riche, Matthieu Duvinage, Matei Mancas et al.

Since the early 2000s, computational visual saliency has been a very active research area. Each year, more and more new models are published in the main computer vision conferences. Nowadays, one of the big challenges is to find a way to fairly evaluate all of these models. In this paper, a new framework is proposed to assess models of visual saliency. This evaluation is divided into three experiments leading to the proposition of a new evaluation framework. Each experiment is based on a basic question: 1) there are two ground truths for saliency evaluation: what are the differences between eye fixations and manually segmented salient regions?, 2) the properties of the salient regions: for example, do large, medium and small salient regions present different difficulties for saliency models? and 3) the metrics used to assess saliency models: what advantages would there be to mix them with PCA? Statistical analysis is used here to answer each of these three questions.