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.

Methods to improve noise robustness of speech recognition systems often result in degradation of recognition performance for clean speech. Recently proposed Phase AutoCorrelation (PAC) \cite{ikbal03,ikbal03a} based features, showing noticeable improvement in noise robustness, also suffer from this draw back. In this paper, we try to alleviate this problem by using the PAC based features along with regular speech features in a multi-stream framework. The multi-stream system uses entropy of the posterior prob

Sparse Component Analysis is a relatively young technique that relies upon a representation of signal occupying only a small part of a larger space. Mixtures of sparse components are disjoint in that space. As a particular application of sparsity of speech signals, we investigate the DUET blind source separation algorithm in the context of speech recognition for multi-party recordings. We show how DUET can be tuned to the particular case of speech recognition with interfering sources, and evaluate the limit

Spatial filtering is the fundamental characteristic of microphone array based signal acquisition, which plays an important role in applications such as speech enhancement and distant speech recognition. In the array processing literature, this property is formulated upon beam-pattern steering and it is characterized for narrowband signals. This paper proposes to characterize the microphone array broadband beam-pattern based on the average output of a steered beamformer for a broadband spectrum. Relying on t

Multi-band speech recognition is powerful in band-limited noise, when the recognizer of the noisy band, which is less reliable, can be given less weight in the recombination process. An accurate decision on which bands can be considered as reliable and which bands are less reliable due to corruption by noise is usually hard to take. In this article, we investigate a maximum-likelihood (ML) approach to adapting the combination weights of a multi-band system. The Gaussian Mixture Model parameters are kept con

In this paper, we present an entropy based method to combine tandem representations of the recently proposed Phase AutoCorrelation (PAC) based features and Mel-Frequency Cepstral Coefficients (MFCC) features. PAC based features, derived from a nonlinear transformation of autocorrelation coefficients and shown to be noise robust, improve their robustness to additive noise in their tandem representation. On the other hand, MFCC features in their tandem representation show a significant improvement in recognit

We address the problem of microphone location cali- bration where the sensor positions have a sparse spatial approximation on a discretized grid. We characterize the microphone signals as a sparse vector represented over a codebook of multi-channel signals ...

Multistream diarization is an effective way to improve the diarization performance, MFCC and Time Delay Of Arrivals (TDOA) being the most commonly used features. This paper extends our previous work on information bottleneck diarization aiming to include large number of features besides MFCC and TDOA while keeping computational costs low. At first HMM/GMM and IB systems are compared in case of two and four feature streams and analysis of errors is performed. Results on a dataset of 17 meetings show that, in

The goal of this paper is to investigate features for speech/nonspeech detection (SND) having low linguistic information from the speech signal. Towards this, we present a comprehensive study of privacy-sensitive features for SND in multiparty conversation ...

This paper investigates the use of multiple pronunciations modeling for User-Customized Password Speaker Verification (UCP-SV). The main characteristic of the UCP-SV is that the system does not have any {\it a priori} knowledge about the password used by the speaker. Our aim is to exploit the information about how the speaker pronounces a password in the decision process. This information is extracted automatically by using a speaker-independent speech recognizer. In this paper, we investigate and compare s

Standard ASR systems typically use phoneme as the subword units. Preliminary studies have shown that the performance of the ASR system could be improved by using grapheme as additional subword units. In this paper, we investigate such a system where the word models are defined in terms of two different subword units, i.e., phoneme and grapheme. During training, models for both the subword units are trained, and then during recognition either both or just one subword unit is used. We have studied this system

This paper addresses the problem of ad hoc microphone array calibration where only partial information about the distances between the microphones is available. We construct a matrix consisting of the pairwise distances and propose to estimate the missing ...

Multi-stream based automatic speech recognition (ASR) systems outperform their single stream counterparts, specially in case of noisy speech. The main issues in multi-stream systems are: a) Find the feature streams carrying complementary information, and b) Combine the outputs of the classifiers trained on these feature streams. This paper investigates an `oracle' test to address these issues. An interpretation of the oracle test is proposed that can indicate the complimentary of the feature streams used in

This paper investigates a new approach to perform simultaneous speech and speaker recognition. The likelihood estimated by a speaker identification system is combined with the posterior probability estimated by the speech recognizer. So, the joint posterior probability of the pronounced word and the speaker identity is maximized. A comparison study with other standard techniques is carried out in three different applications, (1) closed set speech and speaker identification, (2) open set speech and speaker

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from monolingual context-de ...

Spatial filtering is the fundamental characteristic of microphone array based signal acquisition which plays an important role in applications such as speech enhancement and distant speech recognition. In the array processing literature, this property is formulated upon beam-pattern steering and it is characterized for narrowband signals. This paper proposes to characterize the microphone array broadband beam-pattern based on the average output of a steered beamformer for a broadband spectrum. Relying on th

We cast the query by example spoken term detection (QbE-STD) problem as subspace detection where query and background subspaces are modeled as union of low-dimensional subspaces. The speech exemplars used for subspace modeling are class-conditional posteri ...

Hervé Bourlard

Chat with Graph Search

Phase AutoCorrelation (PAC) features in Entropy based Multi-Stream for Robust Speech Recognition

Sparse Component Analysis for Speech Recognition in Multi-Speaker Environment

Microphone Array Beampattern Characterization for Hands-free Speech Applications

Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR

Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR

Entropy Based Combination of Tandem Representations for Noise Robust ASR

Phase AutoCorrelation (PAC) features in Entropy based Multi-Stream for Robust Speech Recognition

Structured Sparse Coding for Microphone Array Location Calibration

Advances in Fast Multistream Diarization based on the Information Bottleneck Framework

Privacy-Sensitive Audio Features for Speech/Nonspeech Detection

Confidence Measures in Multiple pronunciations Modeling For Speaker Verification

Joint Decoding for Phoneme-Grapheme Continuous Speech Recognition

Confidence Measures in Multiple pronunciations Modeling For Speaker Verification

Ad Hoc Microphone Array Calibration: Euclidean Distance Matrix Completion Algorithm and Theoretical Guarantees

Multi-stream ASR: An Oracle Perspective

Posteriori Probabilities and Likelihoods Combination for Speech and Speaker Recognition

Cross-lingual Adaptation of a CTC-based multilingual Acoustic Model

BROADBAND BEAMPATTERN FOR MULTI-CHANNEL SPEECH ACQUISITION AND DISTANT SPEECH RECOGNITION

Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection

Posteriori Probabilities and Likelihoods Combination for Speech and Speaker Recognition