Publications by Hervé Bourlard

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper addresses several issues of classical spectral subtraction methods with respect to the automatic speech recognition task in noisy environments. The main contributions of this paper are twofold. First, a channel normalization method is proposed to extend spectral subtraction to the case of transmission channels such as cellphones. It equalizes the transmission channel and removes part of the additive noise. Second, a simple, computationally efficient \mbox{2-component} probabilistic model is propo

We propose a sparse coding approach to address the problem of source-sensor localization and speech reconstruction. This approach relies on designing a dictionary of spatialized signals by projecting the microphone array recordings into the array manifolds ...

We propose an information theoretic framework for quantitative assessment of acoustic models used in hidden Markov model (HMM) based automatic speech recognition (ASR). The HMM backend expects that (i) the acoustic model yields accurate state conditional e ...

This paper shows that exemplar-based speech processing using class-conditional posterior probabilities admits a highly effective search strategy relying on posteriors' intrinsic sparsity structures. The posterior probabilities are estimated for phonetic and phonological classes using deep neural network (DNN) computational framework. Exploiting the class-specific sparsity leads to a simple quantized posterior hashing procedure to reduce the search space of posterior exemplars. To that end, small number of q

The ability to understand and manage social signals of a person we are communicating with is the core of social intelligence. Social intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for s ...

This article introduces a novel technique for estimating the signal power spectral density to be used in the transfer function of a microphone array post-filter. The technique is a generalisation of the existing Zelinski post-filter, which uses the auto- and cross-spectral densities of the array inputs to estimate the signal and noise spectral densities. The Zelinski technique, however, assumes zero cross-correlation between the noise on different sensors. This assumption is inaccurate, particularly at low

The multi-band processing paradigm for noise robust ASR was originally motivated by the observation that human recognition appears to be based on independent processing of separate frequency sub-bands, and also by

missing data'' results which have shown that ASR can be made significantly more robust to band-limited noise if noisy sub-bands can be detected and then ignored. Of the different multi-band models which have been proposed, only the

Full Combination'' or ``all-wise'' multi-band HMM/ANN hybrid a

missing data'' results which have shown that ASR can be made significantly more robust to band-limited noise if noisy sub-bands can be detected and then ignored. Of the different multi-band models which have been proposed, only the

Full Combination'' or ``all-wise'' multi-band HMM/ANN hybrid a

HMM2 is a particular hidden Markov model where state emission probabilities of the temporal (primary) HMM are modeled through (secondary) state-dependent frequency-based HMMs [12]. As shown in [13], a secondary HMM can also be used to extract robust ASR features. Here, we further investigate this novel approach towards using a full HMM2 as feature extractor, working in the spectral domain, and extracting robust formant-like features for standard ASR system. HMM2 performs a nonlinear, state-dependent frequen

In this paper, a compressive sensing (CS) perspective to exemplar-based speech processing is proposed. Relying on an analytical relationship between CS formulation and statistical speech recognition (Hidden Markov Models HMM), the automatic speech recognit ...

It is often acknowledged that speech signals contain short-term and long-term temporal properties that are difficult to capture and model by using the usual fixed scale (typically 20ms) short time spectral analysis used in hidden Markov models (HMMs), based on piecewise stationarity and state conditional independence assumptions of acoustic vectors. For example, vowels are typically quasi-stationary over 40-80ms segments, while plosives typically require analysis below 20ms segments. Thus, fixed scale analy

In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoacoustics, multi-band ASR aims for robustness to data mismatch through the exploitation of spectral redundancy, while making minimum assumptions about noise type. Previous ASR tests have shown that independent sub-band processing can lead to decreased recog

In this paper, we present a robust speech acquisition system to acquire continuous speech using a microphone array. A microphone array based speech recognition system is also presented to study the environmental interference due to reverberation, background noises and mismatch between the training and testing conditions. This is important in the context of smart meeting rooms of Augmented MultiParty Interaction (AMI) project which aims at significant development of conversational speech recognition. In this

We hypothesize that optimal deep neural networks (DNN) class-conditional posterior probabilities live in a union of low-dimensional subspaces. In real test conditions, DNN posteriors encode uncertainties which can be regarded as a superposition of unstructured sparse noise to the optimal posteriors. We aim to investigate different ways to structure the DNN outputs exploiting low-rank representation (LRR) techniques. Using a large number of training posterior vectors, the underlying low-dimensional subspace

We tackle the multi-party speech recovery problem through modeling the acoustic of the reverberant chambers. Our approach exploits structured sparsity models to perform room modeling and speech recovery. We propose a scheme for characterizing the room acou ...

A speaker diarization system based on an information theoretic framework is described. The problem is formulated according to the Information Bottleneck (IB) principle. Unlike other approaches where the distance between speaker segments is arbitrarily intr ...

In this paper, we describe recent work at Idiap Research Institute in the domain of multilingual speech processing and provide some insights into emerging challenges for the research community. Multilingual speech processing has been a topic of ongoing int ...

Hervé Bourlard

Chat with Graph Search

Unsupervised Spectral Subtraction for Noise-Robust ASR on Unknown Transmission Channels

Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures

Social Signal Processing: Survey of an Emerging Domain

Microphone Array Post-filter based on Noise Field Coherence

Microphone Array Post-filter based on Noise Field Coherence

From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR

From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR

Speech Recognition Using Advanced HMM2 Features

Speech Recognition Using Advanced HMM2 Features

Sparse Modeling of Neural Network Posterior Probabilities for Exemplar-based Speech Recognition

On Variable-Scale Piecewise Stationary Spectral Analysis of Speech Signals for ASR

Multi-stream adaptive evidence combination for noise robust ASR

Multi-stream adaptive evidence combination for noise robust ASR

Continuous Microphone Array Speech Recognition on Wall Street Journal Corpus

Low-Rank Representation of Nearest Neighbor Phone Posterior Probabilities to Enhance DNN Acoustic Modeling

Structured Sparsity Models for Reverberant Speech Separation

An Information Theoretic Approach to Speaker Diarization of Meeting Data

Current trends in multilingual speech processing