Nicolas Obin

Mireille Fares, Michele Grimaldi, Catherine Pelachaud et al.

Modeling virtual agents with behavior style is one factor for personalizing human agent interaction. We propose an efficient yet effective machine learning approach to synthesize gestures driven by prosodic features and text in the style of different speakers including those unseen during training. Our model performs zero shot multimodal style transfer driven by multimodal data from the PATS database containing videos of various speakers. We view style as being pervasive while speaking, it colors the communicative behaviors expressivity while speech content is carried by multimodal signals and text. This disentanglement scheme of content and style allows us to directly infer the style embedding even of speaker whose data are not part of the training phase, without requiring any further training or fine tuning. The first goal of our model is to generate the gestures of a source speaker based on the content of two audio and text modalities. The second goal is to condition the source speaker predicted gestures on the multimodal behavior style embedding of a target speaker. The third goal is to allow zero shot style transfer of speakers unseen during training without retraining the model. Our system consists of: (1) a speaker style encoder network that learns to generate a fixed dimensional speaker embedding style from a target speaker multimodal data and (2) a sequence to sequence synthesis network that synthesizes gestures based on the content of the input modalities of a source speaker and conditioned on the speaker style embedding. We evaluate that our model can synthesize gestures of a source speaker and transfer the knowledge of target speaker style variability to the gesture generation task in a zero shot setup. We convert the 2D gestures to 3D poses and produce 3D animations. We conduct objective and subjective evaluations to validate our approach and compare it with a baseline.

Mireille Fares, Catherine Pelachaud, Nicolas Obin

This paper addresses the challenge of transferring the behavior expressivity style of a virtual agent to another one while preserving behaviors shape as they carry communicative meaning. Behavior expressivity style is viewed here as the qualitative properties of behaviors. We propose TranSTYLer, a multimodal transformer based model that synthesizes the multimodal behaviors of a source speaker with the style of a target speaker. We assume that behavior expressivity style is encoded across various modalities of communication, including text, speech, body gestures, and facial expressions. The model employs a style and content disentanglement schema to ensure that the transferred style does not interfere with the meaning conveyed by the source behaviors. Our approach eliminates the need for style labels and allows the generalization to styles that have not been seen during the training phase. We train our model on the PATS corpus, which we extended to include dialog acts and 2D facial landmarks. Objective and subjective evaluations show that our model outperforms state of the art models in style transfer for both seen and unseen styles during training. To tackle the issues of style and content leakage that may arise, we propose a methodology to assess the degree to which behavior and gestures associated with the target style are successfully transferred, while ensuring the preservation of the ones related to the source content.

Mireille Fares, Catherine Pelachaud, Nicolas Obin

Image Schemas are repetitive cognitive patterns that influence the way we conceptualize and reason about various concepts present in speech. These patterns are deeply embedded within our cognitive processes and are reflected in our bodily expressions including gestures. Particularly, metaphoric gestures possess essential characteristics and semantic meanings that align with Image Schemas, to visually represent abstract concepts. The shape and form of gestures can convey abstract concepts, such as extending the forearm and hand or tracing a line with hand movements to visually represent the image schema of PATH. Previous behavior generation models have primarily focused on utilizing speech (acoustic features and text) to drive the generation model of virtual agents. They have not considered key semantic information as those carried by Image Schemas to effectively generate metaphoric gestures. To address this limitation, we introduce META4, a deep learning approach that generates metaphoric gestures from both speech and Image Schemas. Our approach has two primary goals: computing Image Schemas from input text to capture the underlying semantic and metaphorical meaning, and generating metaphoric gestures driven by speech and the computed image schemas. Our approach is the first method for generating speech driven metaphoric gestures while leveraging the potential of Image Schemas. We demonstrate the effectiveness of our approach and highlight the importance of both speech and image schemas in modeling metaphoric gestures.

Théodor Lemerle, Nicolas Obin, Axel Roebel

Recent advancements in text-to-speech (TTS) powered by language models have showcased remarkable capabilities in achieving naturalness and zero-shot voice cloning. Notably, the decoder-only transformer is the prominent architecture in this domain. However, transformers face challenges stemming from their quadratic complexity in sequence length, impeding training on lengthy sequences and resource-constrained hardware. Moreover they lack specific inductive bias with regards to the monotonic nature of TTS alignments. In response, we propose to replace transformers with emerging recurrent architectures and introduce specialized cross-attention mechanisms for reducing repeating and skipping issues. Consequently our architecture can be efficiently trained on long samples and achieve state-of-the-art zero-shot voice cloning against baselines of comparable size. Our implementation and demos are available at https://github.com/theodorblackbird/lina-speech.

Théodor Lemerle, Téo Guichoux, Axel Roebel et al.

Neural codec language models, built on transformer architecture, have revolutionized text-to-speech (TTS) synthesis, excelling in voice cloning by treating it as a prefix continuation task. However, their limited context length hinders their effectiveness to short speech samples. As a result, the voice cloning ability is restricted to a limited coverage and diversity of the speaker's prosody and style. Besides, adapting prosody, accent, or appropriate emotion from a short prefix remains a challenging task. Finally, the quadratic complexity of self-attention limits inference throughput. In this work, we introduce Lina-Speech, a TTS model with Gated Linear Attention (GLA) to replace standard self-attention as a principled backbone, improving inference throughput while matching state-of-the-art performance. Leveraging the stateful property of recurrent architecture, we introduce an Initial-State Tuning (IST) strategy that unlocks the possibility of multiple speech sample conditioning of arbitrary numbers and lengths and provides a comprehensive and efficient strategy for voice cloning and out-of-domain speaking style and emotion adaptation. We demonstrate the effectiveness of this approach for controlling fine-grained characteristics such as prosody and emotion. Code, checkpoints, and demo are freely available: https://github.com/theodorblackbird/lina-speech

Téo Guichoux, Laure Soulier, Nicolas Obin et al.

Co-speech gestures are fundamental for communication. The advent of recent deep learning techniques has facilitated the creation of lifelike, synchronous co-speech gestures for Embodied Conversational Agents. "In-the-wild" datasets, aggregating video content from platforms like YouTube via human pose detection technologies, provide a feasible solution by offering 2D skeletal sequences aligned with speech. Concurrent developments in lifting models enable the conversion of these 2D sequences into 3D gesture databases. However, it is important to note that the 3D poses estimated from the 2D extracted poses are, in essence, approximations of the ground-truth, which remains in the 2D domain. This distinction raises questions about the impact of gesture representation dimensionality on the quality of generated motions - a topic that, to our knowledge, remains largely unexplored. Our study examines the effect of using either 2D or 3D joint coordinates as training data on the performance of speech-to-gesture deep generative models. We employ a lifting model for converting generated 2D pose sequences into 3D and assess how gestures created directly in 3D stack up against those initially generated in 2D and then converted to 3D. We perform an objective evaluation using widely used metrics in the gesture generation field as well as a user study to qualitatively evaluate the different approaches.

Mathilde Abrassart, Nicolas Obin, Axel Roebel

Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important element for effective identity conversion, but can also be used independently for voice transformation, achieving goals that were historically addressed by vocoder-based methods. In this work, we explore a convolutional neural network-based approach that aims to provide means for modifying fundamental frequency (F0), phoneme sequences, intensity, and speaker identity. Rather than relying on disentanglement techniques, our model is explicitly conditioned on these factors to generate mel spectrograms, which are then converted into waveforms using a universal neural vocoder. Accordingly, during inference, F0 contours, phoneme sequences, and speaker embeddings can be freely adjusted, allowing for intuitively controlled voice transformations. We evaluate our approach on speaker conversion and expressive speech tasks using both perceptual and objective metrics. The results suggest that the proposed method offers substantial flexibility, while maintaining high intelligibility and speaker similarity.

Diego Torres, Axel Roebel, Nicolas Obin

We present PitchFlower, a flow-based neural audio codec with explicit pitch controllability. Our approach enforces disentanglement through a simple perturbation: during training, F0 contours are flattened and randomly shifted, while the true F0 is provided as conditioning. A vector-quantization bottleneck prevents pitch recovery, and a flow-based decoder generates high quality audio. Experiments show that PitchFlower achieves more accurate pitch control than WORLD at much higher audio quality, and outperforms SiFiGAN in controllability while maintaining comparable quality. Beyond pitch, this framework provides a simple and extensible path toward disentangling other speech attributes.

Téo Guichoux, Théodor Lemerle, Shivam Mehta et al.

Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a unified framework that jointly synthesizes speech and co-speech gestures from text using interleaved token sequences in a discrete autoregressive backbone, with modality-specific decoders. Gelina supports multi-speaker and multi-style cloning and enables gesture-only synthesis from speech inputs. Subjective and objective evaluations demonstrate competitive speech quality and improved gesture generation over unimodal baselines.

Balthazar Bujard, Jérôme Nika, Fédéric Bevilacqua et al.

This paper presents the first step in a research project situated within the field of musical agents. The objective is to achieve, through training, the tuning of the desired musical relationship between a live musical input and a real-time generated musical output, through the curation of a database of separated tracks. We propose an architecture integrating a symbolic decision module capable of learning and exploiting musical relationships from such musical corpus. We detail an offline implementation of this architecture employing Transformers as the decision module, associated with a perception module based on Wav2Vec 2.0, and concatenative synthesis as audio renderer. We present a quantitative evaluation of the decision module's ability to reproduce learned relationships extracted during training. We demonstrate that our decision module can predict a coherent track B when conditioned by its corresponding ''guide'' track A, based on a corpus of paired tracks (A, B).

Teo Guichoux, Laure Soulier, Nicolas Obin et al.

Co-speech gestures play a crucial role in the interactions between humans and embodied conversational agents (ECA). Recent deep learning methods enable the generation of realistic, natural co-speech gestures synchronized with speech, but such approaches require large amounts of training data. "In-the-wild" datasets, which compile videos from sources such as YouTube through human pose detection models, offer a solution by providing 2D skeleton sequences that are paired with speech. Concurrently, innovative lifting models have emerged, capable of transforming these 2D pose sequences into their 3D counterparts, leading to large and diverse datasets of 3D gestures. However, the derived 3D pose estimation is essentially a pseudo-ground truth, with the actual ground truth being the 2D motion data. This distinction raises questions about the impact of gesture representation dimensionality on the quality of generated motions, a topic that, to our knowledge, remains largely unexplored. In this work, we evaluate the impact of the dimensionality of the training data, 2D or 3D joint coordinates, on the performance of a multimodal speech-to-gesture deep generative model. We use a lifting model to convert 2D-generated sequences of body pose to 3D. Then, we compare the sequence of gestures generated directly in 3D to the gestures generated in 2D and lifted to 3D as post-processing.

Mireille Fares, Catherine Pelachaud, Nicolas Obin

In this study, we address the importance of modeling behavior style in virtual agents for personalized human-agent interaction. We propose a machine learning approach to synthesize gestures, driven by prosodic features and text, in the style of different speakers, even those unseen during training. Our model incorporates zero-shot multimodal style transfer using multimodal data from the PATS database, which contains videos of diverse speakers. We recognize style as a pervasive element during speech, influencing the expressivity of communicative behaviors, while content is conveyed through multimodal signals and text. By disentangling content and style, we directly infer the style embedding, even for speakers not included in the training phase, without the need for additional training or fine-tuning. Objective and subjective evaluations are conducted to validate our approach and compare it against two baseline methods.

Frederik Bous, Laurent Benaroya, Nicolas Obin et al.

This paper introduces voice reenactement as the task of voice conversion (VC) in which the expressivity of the source speaker is preserved during conversion while the identity of a target speaker is transferred. To do so, an original neural- VC architecture is proposed based on sequence-to-sequence voice conversion (S2S-VC) in which the speech prosody of the source speaker is preserved during conversion. First, the S2S-VC architecture is modified so as to synchronize the converted speech with the source speech by mean of phonetic duration encoding; second, the decoder is conditioned on the desired sequence of F0- values and an explicit F0-loss is formulated between the F0 of the source speaker and the one of the converted speech. Besides, an adversarial learning of conversions is integrated within the S2S-VC architecture so as to exploit both advantages of reconstruction of original speech and converted speech with manipulated attributes during training and then reducing the inconsistency between training and conversion. An experimental evaluation on the VCTK speech database shows that the speech prosody can be efficiently preserved during conversion, and that the proposed adversarial learning consistently improves the conversion and the naturalness of the reenacted speech.

Laurent Benaroya, Nicolas Obin, Axel Roebel

Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged. Research in neural VC has accomplished considerable breakthroughs with the capacity to falsify a voice identity using a small amount of data with a highly realistic rendering. This paper goes beyond voice identity and presents a neural architecture that allows the manipulation of voice attributes (e.g., gender and age). Leveraging the latest advances on adversarial learning of structured speech representation, a novel structured neural network is proposed in which multiple auto-encoders are used to encode speech as a set of idealistically independent linguistic and extra-linguistic representations, which are learned adversariarly and can be manipulated during VC. Moreover, the proposed architecture is time-synchronized so that the original voice timing is preserved during conversion which allows lip-sync applications. Applied to voice gender conversion on the real-world VCTK dataset, our proposed architecture can learn successfully gender-independent representation and convert the voice gender with a very high efficiency and naturalness.

Clément Le Moine, Nicolas Obin, Axel Roebel

Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific speakers and scenarios is needed, inevitably leading to poorer performances when compared to humans. In this paper, we present novel work based on the idea of teaching the emotion recognition network about speaker identity. Our system is a combination of two ACRNN classifiers respectively dedicated to speaker and emotion recognition. The first informs the latter through a Self Speaker Attention (SSA) mechanism that is shown to considerably help to focus on emotional information of the speech signal. Experiments on social attitudes database Att-HACK and IEMOCAP corpus demonstrate the effectiveness of the proposed method and achieve the state-of-the-art performance in terms of unweighted average recall.

Clément Le Moine Veillon, Nicolas Obin, Axel Roebel

This paper presents a end-to-end framework for the F0 transformation in the context of expressive voice conversion. A single neural network is proposed, in which a first module is used to learn F0 representation over different temporal scales and a second adversarial module is used to learn the transformation from one emotion to another. The first module is composed of a convolution layer with wavelet kernels so that the various temporal scales of F0 variations can be efficiently encoded. The single decomposition/transformation network allows to learn in a end-to-end manner the F0 decomposition that are optimal with respect to the transformation, directly from the raw F0 signal.

Rafael Ferro, Nicolas Obin, Axel Roebel

This paper tackles GAN optimization and stability issues in the context of voice conversion. First, to simplify the conversion task, we propose to use spectral envelopes as inputs. Second we propose two adversarial weight training paradigms, the generalized weighted GAN and the generator impact GAN, both aim at reducing the impact of the generator on the discriminator, so both can learn more gradually and efficiently during training. Applying an energy constraint to the cycleGAN paradigm considerably improved conversion quality. A subjective experiment conducted on a voice conversion task on the voice conversion challenge 2018 dataset shows first that despite a significantly reduced network complexity, the proposed method achieves state-of-the-art results, and second that the proposed weighted GAN methods outperform a previously proposed one.