Pierre-Michel Bousquet

发表

Un Sous-espace Thématique Latent pour la Compréhension du Langage Parlé (A Latent Topic-based Subspace for Spoken Language Understanding)

Mohamed Morchid, Georges Linarès, Killian Janod, 2016, JEP-TALN-RECITAL.

Speaker Modeling Using Local Binary Decisions

Pierre-Michel Bousquet, Jean-François Bonastre, Xavier Anguera Miró, 2011, INTERSPEECH.

Identify the Benefits of the Different Steps in an i-Vector Based Speaker Verification System

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2013, CIARP.

I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences pdf

John H. L. Hansen, Haizhou Li, Chng Eng Siong, 2019, INTERSPEECH.

Intersession Compensation and Scoring Methods in the i-vectors Space for Speaker Recognition

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2011, INTERSPEECH.

LIA System for the SITW Speaker Recognition Challenge

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2016, INTERSPEECH.

Latent Topic-based Subspace for Natural Language Processing

Mohamed Morchid, Killian Janod, Pierre-Michel Bousquet, 2019, J. Signal Process. Syst..

Quaternion Neural Networks for Spoken Language Understanding

Titouan Parcollet, Mohamed Morchid, Georges Linarès, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Session compensation using binary speech representation for speaker recognition

Pierre-Michel Bousquet, Jean-François Bonastre, Gabriel Hernández Sierra, 2014, Pattern Recognit. Lett..

Speaker diarization through speaker embeddings

Mickael Rouvier, Pierre-Michel Bousquet, Benoit Favre, 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

Review of different robust x-vector extractors for speaker verification

Richard Dufour, Mickael Rouvier, Pierre-Michel Bousquet, 2021, 2020 28th European Signal Processing Conference (EUSIPCO).

Spoken Language Understanding in a Latent Topic-Based Subspace

Mohamed Morchid, Georges Linarès, Killian Janod, 2016, INTERSPEECH.

Typicality extraction in a Speaker Binary Keys model

Pierre-Michel Bousquet, Jean-François Bonastre, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Feature selection using Principal Component Analysis for massive retweet detection

Mohamed Morchid, Georges Linarès, Richard Dufour, 2014, Pattern Recognit. Lett..

Adaptation strategy and clustering from scratch for new domains in speaker recognition

Mickael Rouvier, Pierre-Michel Bousquet, 2020 .

Dealing with additive noise in speaker recognition systems based on i-vector approach

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

Analyse en Composante Principale pour l’extraction des i-vecteurs en vérification du locuteur (Principal Component Analysis for i-vector extraction in speaker verification.) [in French]

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2012, JEP/TALN/RECITAL.

I4u submission to NIST SRE 2012: a large-scale collaborative effort for noise-robust speaker verification

John H. L. Hansen, Bin Ma, Haizhou Li, 2013, INTERSPEECH.

The I4U Submission to the 2012 NIST Speaker Recognition Evaluation

John H. L. Hansen, Tomi Kinnunen, Sébastien Marcel, 2012 .

Discriminant binary data representation for speaker recognition

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Duration Mismatch Compensation Using Four-Covariance Model and Deep Neural Network for Speaker Verification

Mickael Rouvier, Pierre-Michel Bousquet, 2017, INTERSPEECH.

Robust Speaker Recognition Using MAP Estimation of Additive Noise in i-vectors Space

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2014, SLSP.

Additive noise compensation in the i-vector space for speaker recognition

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Study of the Effect of I-vector Modeling on Short and Mismatch Utterance Duration for Speaker Verification

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2012, INTERSPEECH.

I-vectors in the context of phonetically-constrained short utterances for speaker verification

Haizhou Li, Kong-Aik Lee, Driss Matrouf, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exploring some limits of Gaussian PLDA modeling for i-vector distributions

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2014, Odyssey.

LIA system description for NIST SRE 2016 pdf

Mickael Rouvier, Driss Matrouf, Pierre-Michel Bousquet, 2016, ArXiv.

Bénéfices et limites des représentations en facteur de variabilité totale pour la reconnaissance du locuteur. (Benefits and limits of the total variability factor representation for speaker recognition)

Pierre-Michel Bousquet, 2014 .

Speaker diarization through speaker embeddings

Mickael Rouvier, Pierre-Michel Bousquet, Benoit Favre, 2015 .

Fast i-vector denoising using MAP estimation and a noise distributions database for robust speaker recognition

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2017, Comput. Speech Lang..

Improving dialogue classification using a topic space representation and a Gaussian classifier based on the decision rule

Mohamed Morchid, Georges Linarès, Renato De Mori, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Variance-spectra based normalization for i-vector standard and probabilistic linear discriminant analysis

Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre, 2012, Odyssey.

On Robustness of Unsupervised Domain Adaptation for Speaker Recognition

Mickael Rouvier, Pierre-Michel Bousquet, Pierre-Michel Bousquet, 2019, INTERSPEECH.

Constrained discriminative speaker verification specific to normalized i-vectors

Pierre-Michel Bousquet, Jean-François Bonastre, 2016, Odyssey.

A bridge between features and evidence for binary attribute-driven perfect privacy pdf

Driss Matrouf, Pierre-Michel Bousquet, Andreas Nautsch, 2021, ArXiv.

Studying squeeze-and-excitation used in CNN for speaker verification pdf

Mickael Rouvier, Pierre-Michel Bousquet, 2021, ArXiv.

Study On the Temporal Pooling Used In Deep Neural Networks For Speaker Verification

Mickael Rouvier, Pierre-Michel Bousquet, Jarod Duret, 2021, 2021 29th European Signal Processing Conference (EUSIPCO).