Ricard Marxer

Clémentin Boittiaux, Ricard Marxer, Claire Dune et al.

Underwater images are altered by the physical characteristics of the medium through which light rays pass before reaching the optical sensor. Scattering and wavelength-dependent absorption significantly modify the captured colors depending on the distance of observed elements to the image plane. In this paper, we aim to recover an image of the scene as if the water had no effect on light propagation. We introduce SUCRe, a novel method that exploits the scene's 3D structure for underwater color restoration. By following points in multiple images and tracking their intensities at different distances to the sensor, we constrain the optimization of the parameters in an underwater image formation model and retrieve unattenuated pixel intensities. We conduct extensive quantitative and qualitative analyses of our approach in a variety of scenarios ranging from natural light to deep-sea environments using three underwater datasets acquired from real-world scenarios and one synthetic dataset. We also compare the performance of the proposed approach with that of a wide range of existing state-of-the-art methods. The results demonstrate a consistent benefit of exploiting multiple views across a spectrum of objective metrics. Our code is publicly available at https://github.com/clementinboittiaux/sucre.

Sergio Burdisso, Séverin Baroudi, Yanis Labrak et al.

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built around a standardized \texttt{Dialog} representation, SDialog provides: (1) persona-driven multi-agent simulation with composable orchestration for controlled, synthetic dialog generation, (2) comprehensive evaluation combining linguistic metrics, LLM-as-a-judge and functional correctness validators, (3) mechanistic interpretability tools for activation inspection and steering via feature ablation and induction, and (4) audio generation with full acoustic simulation including 3D room modeling and microphone effects. The toolkit integrates with all major LLM backends, enabling mixed-backend experiments under a unified API. By coupling generation, evaluation, and interpretability in a dialog-centric architecture, SDialog enables researchers to build, benchmark and understand conversational systems more systematically.

Santiago Cuervo, Adrian Łańcucki, Ricard Marxer et al.

The success of deep learning comes from its ability to capture the hierarchical structure of data by learning high-level representations defined in terms of low-level ones. In this paper we explore self-supervised learning of hierarchical representations of speech by applying multiple levels of Contrastive Predictive Coding (CPC). We observe that simply stacking two CPC models does not yield significant improvements over single-level architectures. Inspired by the fact that speech is often described as a sequence of discrete units unevenly distributed in time, we propose a model in which the output of a low-level CPC module is non-uniformly downsampled to directly minimize the loss of a high-level CPC module. The latter is designed to also enforce a prior of separability and discreteness in its representations by enforcing dissimilarity of successive high-level representations through focused negative sampling, and by quantization of the prediction targets. Accounting for the structure of the speech signal improves upon single-level CPC features and enhances the disentanglement of the learned representations, as measured by downstream speech recognition tasks, while resulting in a meaningful segmentation of the signal that closely resembles phone boundaries.

Clémentin Boittiaux, Ricard Marxer, Claire Dune et al.

Some recent visual-based relocalization algorithms rely on deep learning methods to perform camera pose regression from image data. This paper focuses on the loss functions that embed the error between two poses to perform deep learning based camera pose regression. Existing loss functions are either difficult-to-tune multi-objective functions or present unstable reprojection errors that rely on ground truth 3D scene points and require a two-step training. To deal with these issues, we introduce a novel loss function which is based on a multiplane homography integration. This new function does not require prior initialization and only depends on physically interpretable hyperparameters. Furthermore, the experiments carried out on well established relocalization datasets show that it minimizes best the mean square reprojection error during training when compared with existing loss functions.

Md Sazidur Rahman, David Cabecinhas, Ricard Marxer

Depth information is essential in computer vision, particularly in underwater imaging, robotics, and autonomous navigation. However, conventional augmentation techniques overlook depth aware transformations, limiting model robustness in real world depth variations. In this paper, we introduce Depth-Jitter, a novel depth-based augmentation technique that simulates natural depth variations to improve generalization. Our approach applies adaptive depth offsetting, guided by depth variance thresholds, to generate synthetic depth perturbations while preserving structural integrity. We evaluate Depth-Jitter on two benchmark datasets, FathomNet and UTDAC2020 demonstrating its impact on model stability under diverse depth conditions. Extensive experiments compare Depth-Jitter against traditional augmentation strategies such as ColorJitter, analyzing performance across varying learning rates, encoders, and loss functions. While Depth-Jitter does not always outperform conventional methods in absolute performance, it consistently enhances model stability and generalization in depth-sensitive environments. These findings highlight the potential of depth-aware augmentation for real-world applications and provide a foundation for further research into depth-based learning strategies. The proposed technique is publicly available to support advancements in depth-aware augmentation. The code is publicly available on \href{https://github.com/mim-team/Depth-Jitter}{github}.

Santiago Cuervo, Ricard Marxer

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural language models hold for the speech modality, these abilities will improve as the amount of compute used for training increases. In this paper, we use models of this scaling behavior to estimate the scale at which our current methods will yield a SLM with the English proficiency of text-based Large Language Models (LLMs). We establish a strong correlation between pre-training loss and downstream syntactic and semantic performance in SLMs and LLMs, which results in predictable scaling of linguistic performance. We show that the linguistic performance of SLMs scales up to three orders of magnitude more slowly than that of text-based LLMs. Additionally, we study the benefits of synthetic data designed to boost semantic understanding and the effects of coarser speech tokenization.

Pooneh Mousavi, Gallil Maimon, Adel Moumen et al.

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks. They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

Antonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana et al. · mit

Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn an aligned representation space. In this paper, we argue that this phenomenon is caused by the presence of modality-specific information in the representation space. Although some of the most widely used contrastive losses maximize the mutual information between representations of both modalities, they are not designed to remove the modality-specific information. We give a theoretical description of this problem through the lens of the Information Bottleneck Principle. We also empirically analyze how different hyperparameters affect the emergence of this phenomenon in a controlled experimental setup. Finally, we propose a regularization term in the loss function that is derived by means of a variational approximation and aims to increase the representational alignment. We analyze in a set of controlled experiments and real-world applications the advantages of including this regularization term.

Paul Best, Santiago Cuervo, Ricard Marxer

Macroscopic intelligibility models predict the expected human word-error-rate for a given speech-in-noise stimulus. In contrast, microscopic intelligibility models aim to make fine-grained predictions about listeners' perception, e.g. predicting phonetic or lexical responses. State-of-the-art macroscopic models use transfer learning from large scale deep learning models for speech processing, whereas such methods have rarely been used for microscopic modeling. In this paper, we study the use of transfer learning from Whisper, a state-of-the-art deep learning model for automatic speech recognition, for microscopic intelligibility prediction at the level of lexical responses. Our method outperforms the considered baselines, even in a zero-shot setup, and yields a relative improvement of up to 66\% when fine-tuned to predict listeners' responses. Our results showcase the promise of large scale deep learning based methods for microscopic intelligibility prediction.

Yanis Labrak, David Grünert, Séverin Baroudi et al.

Long-context audio reasoning is underserved in both training data and evaluation. Existing benchmarks target short-context tasks, and the open-ended generation tasks most relevant to long-context reasoning pose well-known challenges for automatic evaluation. We propose a synthetic data generation pipeline designed to serve both as a training resource and as a controlled evaluation environment, and instantiate it for first-visit doctor-patient conversations with SOAP note generation as the task. The pipeline has three stages, persona-driven dialogue generation, multi-speaker audio synthesis with overlap/pause modeling, room acoustics, and sound events, and LLM-based reference SOAP note production, built entirely on open-weight models. We release 8,800 synthetic conversations with 1.3k hours of corresponding audio and reference notes. Evaluating current open-weight systems, we find that cascaded approaches still substantially outperform end-to-end models.

Sameer Khurana, Dominik Klement, Antoine Laurent et al.

We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives: one from a pre-trained speech encoder (HuBERT) for phoneme-level structure, and another from a text-based encoder (LaBSE) for lexical cues. Experiments on English and multilingual data show that HAC's factorized bottleneck yields disentangled token sets: one aligns with phonemes, while another captures word-level semantics. Quantitative evaluations confirm that HAC tokens preserve naturalness and provide interpretable linguistic information, outperforming single-level baselines in both disentanglement and reconstruction quality. These findings underscore HAC's potential as a unified discrete speech representation, bridging acoustic detail and lexical meaning for downstream speech generation and understanding tasks.

Santiago Cuervo, Adel Moumen, Yanis Labrak et al. · mit

Text-Speech Language Models (TSLMs) -- language models trained to jointly process and generate text and speech -- are commonly trained through an early modality fusion/fission approach, in which both modalities are fed and predicted from a shared backbone via linear layers. We hypothesize that this approach limits cross-modal transfer by neglecting feature compositionality -- specifically, the finer-grained nature of speech representations compared to text -- preventing the emergence of a shared feature hierarchy within model layers. In this paper, we argue that this limitation can be addressed through late fusion and fission, with a fission process that accesses both high- and low-level features for speech generation. Our models implementing these principles, SmolTolk, rival or surpass state-of-the-art TSLMs trained with orders of magnitude more compute, and achieve significantly improved cross-modal performance relative to early fusion/fission baselines. Representation analyses further suggest that our method enhances the model's ability to abstract higher-level, more semantic features from speech, and leads to increasingly shared representation spaces across layers.

Jules Cauzinille, Marius Miron, Olivier Pietquin et al.

Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic detection and classification tasks. We show that models such as HuBERT, WavLM, and XEUS can generate rich latent representations of animal sounds across taxa. We analyze the models properties with linear probing on time-averaged representations. We then extend the approach to account for the effect of time-wise information with other downstream architectures. Finally, we study the implication of frequency range and noise on performance. Notably, our results are competitive with fine-tuned bioacoustic pre-trained models and show the impact of noise-robust pre-training setups. These findings highlight the potential of speech-based self-supervised learning as an efficient framework for advancing bioacoustic research.

Santiago Cuervo, Ricard Marxer

Speech foundation models (SFMs) have been benchmarked on many speech processing tasks, often achieving state-of-the-art performance with minimal adaptation. However, the SFM paradigm has been significantly less explored for applications of interest to the speech perception community. In this paper we present a systematic evaluation of 10 SFMs on one such application: Speech intelligibility prediction. We focus on the non-intrusive setup of the Clarity Prediction Challenge 2 (CPC2), where the task is to predict the percentage of words correctly perceived by hearing-impaired listeners from speech-in-noise recordings. We propose a simple method that learns a lightweight specialized prediction head on top of frozen SFMs to approach the problem. Our results reveal statistically significant differences in performance across SFMs. Our method resulted in the winning submission in the CPC2, demonstrating its promise for speech perception applications.

Clémentin Boittiaux, Claire Dune, Maxime Ferrera et al.

Visual localization plays an important role in the positioning and navigation of robotics systems within previously visited environments. When visits occur over long periods of time, changes in the environment related to seasons or day-night cycles present a major challenge. Under water, the sources of variability are due to other factors such as water conditions or growth of marine organisms. Yet it remains a major obstacle and a much less studied one, partly due to the lack of data. This paper presents a new deep-sea dataset to benchmark underwater long-term visual localization. The dataset is composed of images from four visits to the same hydrothermal vent edifice over the course of five years. Camera poses and a common geometry of the scene were estimated using navigation data and Structure-from-Motion. This serves as a reference when evaluating visual localization techniques. An analysis of the data provides insights about the major changes observed throughout the years. Furthermore, several well-established visual localization methods are evaluated on the dataset, showing there is still room for improvement in underwater long-term visual localization. The data is made publicly available at https://www.seanoe.org/data/00810/92226/.

Santiago Cuervo, Maciej Grabias, Jan Chorowski et al.

We investigate the performance on phoneme categorization and phoneme and word segmentation of several self-supervised learning (SSL) methods based on Contrastive Predictive Coding (CPC). Our experiments show that with the existing algorithms there is a trade off between categorization and segmentation performance. We investigate the source of this conflict and conclude that the use of context building networks, albeit necessary for superior performance on categorization tasks, harms segmentation performance by causing a temporal shift on the learned representations. Aiming to bridge this gap, we take inspiration from the leading approach on segmentation, which simultaneously models the speech signal at the frame and phoneme level, and incorporate multi-level modelling into Aligned CPC (ACPC), a variation of CPC which exhibits the best performance on categorization tasks. Our multi-level ACPC (mACPC) improves in all categorization metrics and achieves state-of-the-art performance in word segmentation.

Jan Chorowski, Grzegorz Ciesielski, Jarosław Dzikowski et al.

We present a number of low-resource approaches to the tasks of the Zero Resource Speech Challenge 2021. We build on the unsupervised representations of speech proposed by the organizers as a baseline, derived from CPC and clustered with the k-means algorithm. We demonstrate that simple methods of refining those representations can narrow the gap, or even improve upon the solutions which use a high computational budget. The results lead to the conclusion that the CPC-derived representations are still too noisy for training language models, but stable enough for simpler forms of pattern matching and retrieval.

Jan Chorowski, Grzegorz Ciesielski, Jarosław Dzikowski et al.

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations. Rather than producing individual predictions for each of the future representations, the model emits a sequence of predictions shorter than that of the upcoming representations to which they will be aligned. In this way, the prediction network solves a simpler task of predicting the next symbols, but not their exact timing, while the encoding network is trained to produce piece-wise constant latent codes. We evaluate the model on a speech coding task and demonstrate that the proposed Aligned Contrastive Predictive Coding (ACPC) leads to higher linear phone prediction accuracy and lower ABX error rates, while being slightly faster to train due to the reduced number of prediction heads.

Sameer Khurana, Antoine Laurent, Wei-Ning Hsu et al.

Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. LVMs admit an intuitive probabilistic interpretation where the latent structure shapes the information extracted from the signal. Even though LVMs have recently seen a renewed interest due to the introduction of Variational Autoencoders (VAEs), their use for speech representation learning remains largely unexplored. In this work, we propose Convolutional Deep Markov Model (ConvDMM), a Gaussian state-space model with non-linear emission and transition functions modelled by deep neural networks. This unsupervised model is trained using black box variational inference. A deep convolutional neural network is used as an inference network for structured variational approximation. When trained on a large scale speech dataset (LibriSpeech), ConvDMM produces features that significantly outperform multiple self-supervised feature extracting methods on linear phone classification and recognition on the Wall Street Journal dataset. Furthermore, we found that ConvDMM complements self-supervised methods like Wav2Vec and PASE, improving on the results achieved with any of the methods alone. Lastly, we find that ConvDMM features enable learning better phone recognizers than any other features in an extreme low-resource regime with few labeled training examples.

Adrian Łańcucki, Jan Chorowski, Guillaume Sanchez et al.

In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial representations of speech, applicable to unsupervised voice conversion and reaching state-of-the-art performance on unit discovery tasks. For unsupervised representation learning, they became viable alternatives to continuous latent variable models such as the Variational Auto-Encoder (VAE). However, training deep discrete variable models is challenging, due to the inherent non-differentiability of the discretization operation. In this paper we focus on VQ-VAE, a state-of-the-art discrete bottleneck model shown to perform on par with its continuous counterparts. It quantizes encoder outputs with on-line $k$-means clustering. We show that the codebook learning can suffer from poor initialization and non-stationarity of clustered encoder outputs. We demonstrate that these can be successfully overcome by increasing the learning rate for the codebook and periodic date-dependent codeword re-initialization. As a result, we achieve more robust training across different tasks, and significantly increase the usage of latent codewords even for large codebooks. This has practical benefit, for instance, in unsupervised representation learning, where large codebooks may lead to disentanglement of latent representations.

Guillaume Sanchez, Vincente Guis, Ricard Marxer et al.

Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval, classification or recommendation can involve tagging or classification based on multiple criteria. In our case, we train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators (actors unknown to our database). Face classifiers are known to be sensitive to label noise. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.

Mandar Gogate, Ahsan Adeel, Ricard Marxer et al.

Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features extraction and ideal binary mask (IBM) estimation, a hybrid DNN architecture is exploited to leverages the complementary strengths of a stacked long short term memory (LSTM) and convolution LSTM network. The comparative simulation results in terms of speech quality and intelligibility demonstrate significant performance improvement of our proposed AV mask estimation model as compared to audio-only and visual-only mask estimation approaches for both speaker dependent and independent scenarios.

Ricard Marxer, Hendrik Purwins

A system is presented that segments, clusters and predicts musical audio in an unsupervised manner, adjusting the number of (timbre) clusters instantaneously to the audio input. A sequence learning algorithm adapts its structure to a dynamically changing clustering tree. The flow of the system is as follows: 1) segmentation by onset detection, 2) timbre representation of each segment by Mel frequency cepstrum coefficients, 3) discretization by incremental clustering, yielding a tree of different sound classes (e.g. instruments) that can grow or shrink on the fly driven by the instantaneous sound events, resulting in a discrete symbol sequence, 4) extraction of statistical regularities of the symbol sequence, using hierarchical N-grams and the newly introduced conceptual Boltzmann machine, and 5) prediction of the next sound event in the sequence. The system's robustness is assessed with respect to complexity and noisiness of the signal. Clustering in isolation yields an adjusted Rand index (ARI) of 82.7% / 85.7% for data sets of singing voice and drums. Onset detection jointly with clustering achieve an ARI of 81.3% / 76.3% and the prediction of the entire system yields an ARI of 27.2% / 39.2%.