Jean-Luc Gauvain

Also known as Gauvain Jean-Luc

Jean-Luc Gauvain is a speech researcher whose work centers on automatic speech recognition. He earned a doctorate in electronics at Paris-Sud University in 1982 and joined CNRS at LIMSI in 1983. During a 1990–1991 visit to AT&T Bell Laboratories, he worked with Chin-Hui Lee on Bayesian hidden Markov models for speech recognition. He coauthored LIMSI's 1994 dictation paper and co-edited Speech Communication from 2006 to 2008; the CNRS awarded him its silver medal in 2007, and he coordinated Quaero from 2008 to 2013. ISCA named him a Fellow in 2017; by 2018, he led LIMSI's Spoken Language Processing Group, and as of October 2026, he is an emeritus researcher in LISN's LIPS group.

Now at: Interdisciplinary Laboratory of Digital Sciences

Timeline

1982–1983

A doctorate at Paris-Sud

He earns a doctorate in electronics at Paris-Sud University in 1982 and joins CNRS at LIMSI as a permanent researcher in 1983.
1990–1991

Bayesian models for speech recognition

From June 1990 to November 1991, he visits AT&T Bell Laboratories. With Chin-Hui Lee, he develops Bayesian learning methods for continuous-density hidden Markov models that support parameter smoothing, speaker adaptation, speaker clustering, and corrective training for speech recognition.
March 1994

LIMSI speech dictation system

In March 1994, he and colleagues present the LIMSI continuous speech dictation system, a multilingual, speaker-independent, large-vocabulary recognizer. The paper describes the recognizer's evaluation in the ARPA NOV93 CSR test.
2006–2008

Speech Communication and a CNRS medal

From 2006 to 2008, he serves as co-editor-in-chief of the journal Speech Communication. The CNRS awards him its silver medal in 2007.
2008–2013

Coordinating Quaero

He serves as scientific coordinator for the Quaero research programme from 2008 to 2013.
2017

An ISCA Fellowship

ISCA names him a Fellow in 2017 for his contributions to automatic speech recognition.
By 2018

Leading LIMSI's speech group

By 2018, he heads the Spoken Language Processing Group at LIMSI.
As of October 2026

Emeritus at LISN

As of October 2026, he is a researcher emeritus in LISN's LIPS group. His group's research includes speaker recognition, which identifies who spoke when in multimedia documents.