Emmanuel Vincent

• PhD
• National Institute for Research in Computer Science and Control

In this paper, we investigate the impact of speech temporal dynamics in application to automatic speaker verification and speaker voice anonymization tasks. We propose several metrics to perform automatic speaker verification based only on phoneme durations. Experimental results demonstrate that phoneme durations leak some speaker information and c...

The First VoicePrivacy Attacker Challenge is a new kind of challenge organized as part of the VoicePrivacy initiative and supported by ICASSP 2025 as the SP Grand Challenge It focuses on developing attacker systems against voice anonymization, which will be evaluated against a set of anonymization systems submitted to the VoicePrivacy 2024 Challeng...

The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation task and datasets used for system development and evaluation, present the different attack models used for eva...

The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation task and datasets used for system development and evaluation, present the different attack models used for eva...

Learning-based methods have become ubiquitous in sound source localization (SSL). Existing systems rely on simulated training sets for the lack of sufficiently large, diverse and annotated real datasets. Most room acoustic simulators used for this purpose rely on the image source method (ISM) because of its computational efficiency. This paper argu...

Blind acoustic parameter estimation consists in inferring the acoustic properties of an environment from recordings of unknown sound sources. Recent works in this area have utilized deep neural networks trained either partially or exclusively on simulated data, due to the limited availability of real annotated measurements. In this paper, we study...

The VoicePrivacy Challenge aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this document, we formulate the voice anonymization task selected for the VoicePriva...

For new participants - Executive summary: (1) The task is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content, paralinguistic attributes, intelligibility and naturalness. (2) Training, development and evaluation datasets are provided in addition to 3 different basel...

Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information from a speech utterance while leaving its linguistic and prosodic attributes intact. State-of-the-art techniq...

This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results. In particular, we describe the voice anonymization task and...

We study the scenario where individuals ( speakers ) contribute to the publication of an anonymized speech corpus. Data users leverage this public corpus for downstream tasks, e.g., training an automatic speech recognition (ASR) system, while attackers may attempt to de-anonymize it using auxiliary knowledge. Motivated by this scenario, speake...

We study the problem of detecting and counting simultaneous, overlapping speakers in a multichannel, distant-microphone scenario. Focusing on a supervised learning approach, we treat Voice Activity Detection (VAD), Overlapped Speech Detection (OSD), joint VAD and OSD (VAD+OSD) and speaker counting in a unified way, as instances of a general Overlap...

For many decades, research in speech technologies has focused upon improving reliability. With this now meeting user expectations for a range of diverse applications, speech technology is today omni-present. As result, a focus on security and privacy has now come to the fore. Here, the research effort is in its relative infancy and progress calls f...

This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results. In particular, we describe the voice anonymization task and...

Knowing the geometrical and acoustical parameters of a room may benefit applications such as audio augmented reality, speech dereverberation or audio forensics. In this paper, we study the problem of jointly estimating the total surface area, the volume, as well as the frequency-dependent reverberation time and mean surface absorption of a room in...

The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this paper, we formulate the voice anonymization task selected for the VoicePrivacy...

In this work, we present the system description of the UIAI entry for the short-duration speaker verification (SdSV) challenge 2020. Our focus is on Task 1 dedicated to text-dependent speaker verification. We investigate different feature extraction and modeling approaches for automatic speaker verification (ASV) and utterance verification (UV). We...

In this work, we present the system description of the UIAI entry for the short-duration speaker verification (SdSV) challenge 2020. Our focus is on Task 1 dedicated to text-dependent speaker verification. We investigate different feature extraction and modeling approaches for automatic speaker verification (ASV) and utterance verification (UV). We...

We consider the problem of simultaneous reduction of acoustic echo, reverberation and noise. In real scenarios, these distortion sources may occur simultaneously and reducing them implies combining the corresponding distortion-specific filters. As these filters interact with each other, they must be jointly optimized. We propose to model the target...

In recent years, wsj0-2mix has become the reference dataset for single-channel speech separation. Most deep learning-based speech separation models today are benchmarked on it. However, recent studies have shown important performance drops when models trained on wsj0-2mix are evaluated on other, similar datasets. To address this generalization issu...

The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker selection technique as a baseline for the first VoicePrivacy Challenge. We explore several design choices for the distance metric between speakers, the region of x-vector space...

Ambient sound scenes typically comprise multiple short events occurring on top of a somewhat stationary background. We consider the task of separating these events from the background, which we call foreground-background ambient sound scene separation. We propose a deep learning-based separation framework with a suitable feature normaliza-tion sche...

This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve reproducibility, Kaldi-style recipes on common audio source separation datasets are also provided. This...

The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this paper, we formulate the voice anonymization task selected for the VoicePrivacy...

Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge revisits the previous CHiME-5 challenge and further considers the problem of distant multi-microphone conversational speech diarization and recognition in everyday home environme...

This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, which considerably outperformed the challenge baselines, we also focus on the lessons learned from numerous approaches that we tried for single and multi-channel systems. We...

Speech separation is the process of separating multiple speakers from an audio recording. In this work we propose to separate the sources using a Speaker LOcalization Guided Deflation (SLOGD) approach wherein we estimate the sources iteratively. In each iteration we first estimate the location of the speaker and use it to estimate a mask correspond...

We present a new, extended version of the voiceHome corpus for distant-microphone speech processing in domestic environments. This 5-hour corpus includes short reverberated, noisy utterances (smart home commands) spoken in French by 12 native French talkers in diverse realistic acoustic conditions and recorded by an 8-microphone device at various a...

The CHiME challenge series aims to advance robust automatic speech recognition (ASR) technology by promoting research at the interface of speech and language processing, signal processing , and machine learning. This paper introduces the 5th CHiME Challenge, which considers the task of distant multi-microphone conversational ASR in real home enviro...

The CHiME challenge series has been aiming to advance the development of robust automatic speech recognition for use in everyday environments by encouraging research at the interface of signal processing and statistical modelling. The series has been running since 2011 and is now entering its 4th iteration. This chapter provides an overview of the...

Robustness to reverberation is a key concern for distant-microphone ASR. Various approaches have been proposed, including single-channel or multichannel dereverberation, robust feature extraction, alternative acoustic models, and acoustic model adaptation. However, to the best of our knowledge, a detailed study of these techniques in varied reverbe...

This chapter presents a multichannel audio source separation framework where deep neural networks (DNNs) are used to model the source spectra and combined with the classical multichannel Gaussian model to exploit the spatial information. The parameters are estimated in an iterative expectation-maximization (EM) fashion and used to derive a multicha...

Speech enhancement and automatic speech recognition (ASR) are most often evaluated in matched (or multi-condition) settings where the acoustic conditions of the training data match (or cover) those of the test data. Few studies have systematically assessed the impact of acoustic mismatches between training and test data, especially concerning recen...

This paper presents the design and outcomes of the CHiME-3 challenge, the first open speech recognition evaluation designed to target the increasingly relevant multichannel, mobile-device speech recognition scenario. The paper serves two purposes. First, it provides a definitive reference for the challenge, including full descriptions of the task d...

This article addresses the problem of multichannel music separation. We propose a framework where the source spectra are estimated using deep neural networks and combined with spatial covariance matrices to encode the source spatial characteristics. The parameters are estimated in an iterative expectation-maximization fashion and used to derive a m...

This article addresses the problem of multichannel audio source separation. We propose a framework where deep neural networks (DNNs) are used to model the source spectra and combined with the classical multichannel Gaussian model to exploit the spatial information. The parameters are estimated in an iterative expectation-maximization (EM) fashion a...

Lors du mixage, un morceau de musique est produit à partir du son séparé des différents instruments. La séparation de sources audio cherche à inverser cette étape.

At a large timescale, music pieces can be described as the succession of structural segments which form the global organization of the piece. The present article proposes a model called "System & Contrast", which aims at describing the inner organization of such structural segments in terms of : (i) a carrier system, i.e. a sequence of morphologica...

We consider the framework of uncertainty propagation for automatic speech recognition (ASR) in highly nonstationary noise environments. Uncertainty is considered as the variance of speech distortion. Yet, its accurate estimation in the spectral domain and its propagation to the feature domain remain difficult. Existing methods typically rely on a s...

A wide variety of audio source separation techniques exist and can already tackle many challenging industrial issues. However, in contrast with other application domains, fusion principles were rarely investigated in audio source separation despite their demonstrated potential in classification tasks. In this paper, we propose a general fusion fram...

In order to improve the ASR performance in noisy environments , distorted speech is typically pre-processed by a speech enhancement algorithm, which usually results in a speech estimate containing residual noise and distortion. We may also have some measures of uncertainty or variance of the estimate. Uncertainty decoding is a framework that utiliz...

Multicondition training (MCT) is an established technique to handle noisy and reverberant conditions. Previous works in the field of i-vector based speaker recognition have applied MCT to linear discriminant analysis (LDA) and probabilistic LDA (PLDA), but not to the universal background model (UBM) and the total variability (T) matrix, arguing tha...

We evaluate some recent developments in recurrent neural network (RNN) based speech enhancement in the light of noise-robust automatic speech recognition (ASR). The proposed framework is based on Long Short-Term Memory (LSTM) RNNs which are discriminatively trained according to an optimal speech reconstruction objective. We demonstrate that LSTM sp...

This article considers the problem of online audio source separation. Various algorithms can be found in the literature, featuring either blockwise or stepwise approaches, and using either the spectral or spatial characteristics of the sound sources of a mixture. We offer an algorithm that can combine both stepwise and blockwise approaches, and tha...

This technical report considers the problem of multichannel audio source separation. A few studies have addressed the problem of single-channel audio source separation with deep neural networks (DNNs). We introduce a new framework for multichannel source separation where (1) spectral and spatial parameters are updated iteratively similarly to the e...

We present a general multi-channel source separation framework where additional audio references are available for one (or more) source(s) of a given mixture.Each audio reference is another mixture which is supposed to contain at least one source similar to one of the target sources.Deformations between the sources of interest and their references...

Deep neural networks (DNN) are typically optimized with stochastic gradient descent (SGD) using a fixed learning rate or an adaptive learning rate approach (ADAGRAD). In this paper, we introduce a new learning rule for neural networks that is based on an auxiliary function technique without parameter tuning. Instead of minimizing the objective func...

This book constitutes the proceedings of the 12th International Conference on Latent Variable Analysis and Signal Separation, LVA/ICS 2015, held in Liberec, Czech Republic, in August 2015. The 61 revised full papers presented – 29 accepted as oral presentations and 32 accepted as poster presentations – were carefully reviewed and selected from nume...

A wide variety of audio source separation techniques exists and can already tackle many challenging industrial issues. However, by contrast to other application domains, fusion principles were rarely investigated in audio source separation despite their demonstrated potential in classification tasks. In this paper, we propose a general fusion frame...

Noise-robust automatic speech recognition (ASR) systems rely on feature and/or model compensation. Existing compensation techniques typically operate on the features or on the parameters of the acoustic models themselves. By contrast, a number of normalization techniques have been defined in the field of speaker verification that operate on the res...

Speech and audio signal processing research is a tale of data collection efforts and evaluation campaigns. While large datasets for automatic speech recognition (ASR) in clean environments with various speaking styles are available, the landscape is not as picture- perfect when it comes to robust ASR in realistic environments, much less so for eval...

This paper deals with audio source separation guided by multiple audio references. We present a general framework where additional audio references for one or more sources of a given mixture are available. Each audio reference is another mixture which is supposed to contain at least one source similar to one of the target sources. Deformations betw...

Amongst the speech enhancement techniques, statistical models based on Non-negative Matrix Factorization (NMF) have received great attention. In a single channel configuration, NMF is used to describe the spectral content of both the speech and noise sources. As the number of components can have a crucial influence on separation quality, we here pr...

Non-negative Matrix Factorization (NMF) has become popular in audio source separation in order to design source-specific models. The number of components of the NMF is known to have a noticeable influence on separation quality. Many methods have thus been proposed to select the best order for a given task. To go further, we propose here to use mode...

Audio is a domain where signal separation has long been considered as a fascinating objective, potentially offering a wide range of new possibilities and experiences in professional and personal contexts, by better taking advantage of audio material and finely analyzing complex acoustic scenes. It has thus always been a major area for research in s...

The reverberation time or RT60 is an essential acoustic parameter of a room. In many situations, the room impulse response (RIR) is not available and the RT60 must be blindly estimated from a speech or music signal. Current methods often implicitly assume that reverberation dominates direct sound, which restricts their applicability to relatively s...