Marc-André Carbonneau

Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper

Voice conversion aims to transform source speech into a different target voice. However, typical voice conversion systems do not account for rhythm, which is an important factor in the perception of speaker identity. To bridge this gap, we introduce Urhythmic-an unsupervised method for rhythm conversion that does not require parallel data or text transcriptions. Using self-supervised representations, we first divide source audio into segments approximating sonorants, obstruents, and silences. Then we model rhythm by estimating speaking rate or the duration distribution of each segment type. Finally, we match the target speaking rate or rhythm by time-stretching the speech segments. Experiments show that Urhythmic outperforms existing unsupervised methods in terms of quality and prosody. Code and checkpoints: https://github.com/bshall/urhythmic. Audio demo page: https://ubisoft-laforge.github.io/speech/urhythmic.

Saeed Ghorbani, Ylva Ferstl, Daniel Holden et al.

We present ZeroEGGS, a neural network framework for speech-driven gesture generation with zero-shot style control by example. This means style can be controlled via only a short example motion clip, even for motion styles unseen during training. Our model uses a Variational framework to learn a style embedding, making it easy to modify style through latent space manipulation or blending and scaling of style embeddings. The probabilistic nature of our framework further enables the generation of a variety of outputs given the same input, addressing the stochastic nature of gesture motion. In a series of experiments, we first demonstrate the flexibility and generalizability of our model to new speakers and styles. In a user study, we then show that our model outperforms previous state-of-the-art techniques in naturalness of motion, appropriateness for speech, and style portrayal. Finally, we release a high-quality dataset of full-body gesture motion including fingers, with speech, spanning across 19 different styles.

Gaetan Lopez Latouche, Marc-André Carbonneau, Ben Swanson

Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data for a particular language pair. We propose BinaryAlign, a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios, offering a unifying approach to the task. Additionally, we vary the specific choice of multilingual foundation model, perform stratified error analysis over alignment error type, and explore the performance of BinaryAlign on non-English language pairs. We make our source code publicly available.

Gaetan Lopez Latouche, Marc-André Carbonneau, Ben Swanson

Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, these annotations are unavailable in many low-resource languages. In this paper, we investigate GED in this context. Leveraging the zero-shot cross-lingual transfer capabilities of multilingual pre-trained language models, we train a model using data from a diverse set of languages to generate synthetic errors in other languages. These synthetic error corpora are then used to train a GED model. Specifically we propose a two-stage fine-tuning pipeline where the GED model is first fine-tuned on multilingual synthetic data from target languages followed by fine-tuning on human-annotated GED corpora from source languages. This approach outperforms current state-of-the-art annotation-free GED methods. We also analyse the errors produced by our method and other strong baselines, finding that our approach produces errors that are more diverse and more similar to human errors.

Marc-André Carbonneau, Benjamin van Niekerk, Hugo Seuté et al.

Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing identity. This paper investigates which aspects of a voice are captured in such representations. We find that widely used ASV embeddings focus mainly on static features like timbre and pitch range, while neglecting dynamic elements such as rhythm. We also identify confounding factors that compromise speaker similarity measurements and suggest mitigation strategies. To address these gaps, we propose U3D, a metric that evaluates speakers' dynamic rhythm patterns. This work contributes to the ongoing challenge of assessing speaker identity consistency in the context of ever-better voice cloning systems. We publicly release our code.

Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi et al.

The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and soft speech units as input features. We find that discrete representations effectively remove speaker information but discard some linguistic content - leading to mispronunciations. As a solution, we propose soft speech units. To learn soft units, we predict a distribution over discrete speech units. By modeling uncertainty, soft units capture more content information, improving the intelligibility and naturalness of converted speech. Samples available at https://ubisoft-laforge.github.io/speech/soft-vc/. Code available at https://github.com/bshall/soft-vc/.

Vandad Davoodnia, Saeed Ghorbani, Marc-André Carbonneau et al.

We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without requiring direct 3D annotations. At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information. Our novel cross-view fusion strategy is scalable to any number of cameras, while our synthetic data generation strategy ensures generalization across diverse actors, scenes, and viewpoints. Finally, UPose3D leverages the prediction uncertainty of both the 2D keypoint estimator and the pose compiler module. This provides robustness to outliers and noisy data, resulting in state-of-the-art performance in out-of-distribution settings. In addition, for in-distribution settings, UPose3D yields performance rivalling methods that rely on 3D annotated data while being the state-of-the-art among methods relying only on 2D supervision.

Herman Kamper, Benjamin van Niekerk, Julian Zaïdi et al.

We introduce LinearVC, a simple voice conversion method that sheds light on the structure of self-supervised representations. First, we show that simple linear transformations of self-supervised features effectively convert voices. Next, we probe the geometry of the feature space by constraining the set of allowed transformations. We find that just rotating the features is sufficient for high-quality voice conversion. This suggests that content information is embedded in a low-dimensional subspace which can be linearly transformed to produce a target voice. To validate this hypothesis, we finally propose a method that explicitly factorizes content and speaker information using singular value decomposition; the resulting linear projection with a rank of just 100 gives competitive conversion results. Our work has implications for both practical voice conversion and a broader understanding of self-supervised speech representations. Samples and code: https://www.kamperh.com/linearvc/.

Amin Fadaeinejad, Abdallah Dib, Luiz Gustavo Hafemann et al.

Creating realistic 3D head assets for virtual characters that match a precise artistic vision remains labor-intensive. We present a novel framework that streamlines this process by providing artists with intuitive control over generated 3D heads. Our approach uses a geometry-aware texture synthesis pipeline that learns correlations between head geometry and skin texture maps across different demographics. The framework offers three levels of artistic control: manipulation of overall head geometry, adjustment of skin tone while preserving facial characteristics, and fine-grained editing of details such as wrinkles or facial hair. Our pipeline allows artists to make edits to a single texture map using familiar tools, with our system automatically propagating these changes coherently across the remaining texture maps needed for realistic rendering. Experiments demonstrate that our method produces diverse results with clean geometries. We showcase practical applications focusing on intuitive control for artists, including skin tone adjustments and simplified editing workflows for adding age-related details or removing unwanted features from scanned models. This integrated approach aims to streamline the artistic workflow in virtual character creation.

Julian Zaïdi, Hugo Seuté, Benjamin van Niekerk et al.

This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text. This is one of the most challenging, and rarely directly addressed, task in speech synthesis, especially for highly expressive data. Daft-Exprt uses FiLM conditioning layers to strategically inject different prosodic information in all parts of the architecture. The model explicitly encodes traditional low-level prosody features such as pitch, loudness and duration, but also higher level prosodic information that helps generating convincing voices in highly expressive styles. Speaker identity and prosodic information are disentangled through an adversarial training strategy that enables accurate prosody transfer across speakers. Experimental results show that Daft-Exprt significantly outperforms strong baselines on inter-text cross-speaker prosody transfer tasks, while yielding naturalness comparable to state-of-the-art expressive models. Moreover, results indicate that the model discards speaker identity information from the prosody representation, and consistently generate speech with the desired voice. We publicly release our code and provide speech samples from our experiments.

Antoine Langevin, Marc-André Carbonneau, Mohamed Cheriet et al.

Non-intrusive load monitoring (NILM) is a technique that uses a single sensor to measure the total power consumption of a building. Using an energy disaggregation method, the consumption of individual appliances can be estimated from the aggregate measurement. Recent disaggregation algorithms have significantly improved the performance of NILM systems. However, the generalization capability of these methods to different houses as well as the disaggregation of multi-state appliances are still major challenges. In this paper we address these issues and propose an energy disaggregation approach based on the variational autoencoders framework. The probabilistic encoder makes this approach an efficient model for encoding information relevant to the reconstruction of the target appliance consumption. In particular, the proposed model accurately generates more complex load profiles, thus improving the power signal reconstruction of multi-state appliances. Moreover, its regularized latent space improves the generalization capabilities of the model across different houses. The proposed model is compared to state-of-the-art NILM approaches on the UK-DALE and REFIT datasets, and yields competitive results. The mean absolute error reduces by 18% on average across all appliances compared to the state-of-the-art. The F1-Score increases by more than 11%, showing improvements for the detection of the target appliance in the aggregate measurement.

Marc-André Carbonneau, Julian Zaidi, Jonathan Boilard et al.

Learning to disentangle and represent factors of variation in data is an important problem in AI. While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement. While several metrics exist, little is known on their implicit assumptions, what they truly measure, and their limits. In consequence, it is difficult to interpret results when comparing different representations. In this work, we survey supervised disentanglement metrics and thoroughly analyze them. We propose a new taxonomy in which all metrics fall into one of three families: intervention-based, predictor-based and information-based. We conduct extensive experiments in which we isolate properties of disentangled representations, allowing stratified comparison along several axes. From our experiment results and analysis, we provide insights on relations between disentangled representation properties. Finally, we share guidelines on how to measure disentanglement.

Marc-André Carbonneau, Eric Granger, Ghyslain Gagnon

A growing number of applications, e.g. video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data while some targeted interactions with a domain expert are allowed to improve the training process. In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances. This paper focuses on AL methods for instance classification problems in multiple instance learning (MIL), where data is arranged into sets, called bags, that are weakly labeled. Most AL methods focus on single instance learning problems. These methods are not suitable for MIL problems because they cannot account for the bag structure of data. In this paper, new methods for bag-level aggregation of instance informativeness are proposed for multiple instance active learning (MIAL). The \textit{aggregated informativeness} method identifies the most informative instances based on classifier uncertainty, and queries bags incorporating the most information. The other proposed method, called \textit{cluster-based aggregative sampling}, clusters data hierarchically in the instance space. The informativeness of instances is assessed by considering bag labels, inferred instance labels, and the proportion of labels that remain to be discovered in clusters. Both proposed methods significantly outperform reference methods in extensive experiments using benchmark data from several application domains. Results indicate that using an appropriate strategy to address MIAL problems yields a significant reduction in the number of queries needed to achieve the same level of performance as single instance AL methods.

Marc-André Carbonneau, Veronika Cheplygina, Eric Granger et al.

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.

Marc-André Carbonneau, Eric Granger, Yazid Attabi et al.

Several methods have recently been proposed to analyze speech and automatically infer the personality of the speaker. These methods often rely on prosodic and other hand crafted speech processing features extracted with off-the-shelf toolboxes. To achieve high accuracy, numerous features are typically extracted using complex and highly parameterized algorithms. In this paper, a new method based on feature learning and spectrogram analysis is proposed to simplify the feature extraction process while maintaining a high level of accuracy. The proposed method learns a dictionary of discriminant features from patches extracted in the spectrogram representations of training speech segments. Each speech segment is then encoded using the dictionary, and the resulting feature set is used to perform classification of personality traits. Experiments indicate that the proposed method achieves state-of-the-art results with a significant reduction in complexity when compared to the most recent reference methods. The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 6 parameters can be tuned automatically. In contrast, the simplest reference method uses 4 types of descriptors to which 6 functionals are applied, resulting in over 20 parameters to be tuned.