Continuous Space Language Models for Statistical Machine Translation (2009)
Holger Schwenk, Daniel Dchelotte, Jean-luc Gauvain
Statistical machine translation systems are based on one or more translation models and a language model of the target language. While many different translation models and phrase extraction...
Georges Quenot, Jean-luc Gauvain, Jean-jacques Gangolf, Joseph Mariani
Nous presentons un processeur integrespecialise pour e ectuer les calculs de programmation dynamique pour les systemes de reconnaissance vocale. Ce processeur delivre une puissance de 10 MIPS e caces...
Lori Lamel, Jean-luc Gauvain, Gilles Adda, Claude Barras, Eric Bilinski, Olivier Galibert, ...
This paper describes the speech recognizers evaluated in the TC-STAR Second Evaluation Campaign held in January-February 2006. Systems were developed to transcribe parliamentary speeches in English...
Continuous Space Language Models for Statistical Machine Translation (2008)
Holger Schwenk, Daniel Dchelotte, Jean-luc Gauvain
Statistical machine translation systems are based on one or more translation models and a language model of the target language. While many different translation models and phrase extraction...
The LIMSI SDR System for TREC-9 (2008)
Jean-luc Gauvain, Lori Lamel, Claude Barras, Gilles Adda, Yannick De Kercardio
In this paper we describe the LIMSI Spoken Document Retrieval system used in the TREC-9 evaluation. This system combines an adapted version of the LIMSI 1999 Hub-4E transcription system for speech...
This paper provides an overview of the state-of-the-art in laboratory speaker-independent, large vocabulary continuous speech recognition (LVCSR) systems with a view towards adapting such technology...
was completed while he was visiting Bell Labs in 1990-1991. (2007)
Chin-hui Lee, Jean-luc Gauvain, Jean-luc Gauvain
clustering, corrective training. 19 pages 5 tables 2 Abstract. An investigation into the use of Bayesian learning of the parameters of a multivariate Gaussian mixture density has been carried out. In...
Processing Broadcast Audio for Information Access (2007)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-decker, Claude Barras, Langzhou Chen, ...
This paper addresses recent progress in speaker-independent, large vocabulary, continuous speech recognition, which has opened up a wide range of near and mid-term applications. One rapidly expanding...
USING INFORMATION RETRIEVAL METHODS FOR LANGUAGE MODEL ADAPTATION (2007)
Langzhou Chen, Jean-luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda
In this paper we report experiments on language model adaptation using information retrieval methods, drawing upon recent developments in information extraction and topic tracking. One of the...
Processing Broadcast Audio for Information Access (2007)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-decker, Claude Barras, Langzhou Chen, ...
This paper addresses recent progress in speaker-independent, large vocabulary, continuous speech recognition, which has opened up a wide range of near and mid-term applications. One rapidly expanding...
The LIMSI SDR System for TREC-9 (2007)
Jean-luc Gauvain, Lori Lamel, Claude Barras, Gilles Adda, Yannick De Kercardio
In this paper we describe the LIMSI Spoken Document Retrieval system used in the TREC-9 evaluation. This system combines an adapted version of the LIMSI 1999 Hub-4E transcription system for speech...
An Overview of Speech Recognition Activities at LIMSI (2007)
Jean-luc Gauvain, Gilles Adda, Martine Adda-decker, Claude Barras, Langzhou Chen, Michele Jardino, ...
This paper provides an overview of recent activities at LIMSI in multilingual speech recognition and its applications. The main goal of speech recognition is to provide a transcription of the speech...
Jean-luc Gauvain, Jurgen Den Hartog, Klaus Netter
Abstract. This paper describes the Olive project which aims to support automated indexing of video material by use of human language technologies. Olive is making use of speech recognition to...
Unsupervised Online Adaptation for Speaker Verification (2004)
Over The Telephone, Claude Barras, Sylvain Meignier, Jean-luc Gauvain
This paper presents experiments of unsupervised adaptation for a speaker detection system. The system used is a standard speaker verification system based on cepstral features and Gaussian mixture...
Improving Speaker Diarization (2004)
Claude Barras Xuan, Xuan Zhu, Sylvain Meignier, Jean-luc Gauvain
This paper describes the LIMSI speaker diarization system used in the RT-04F evaluation. The RT-04F system builds upon the LIMSI baseline data partitioner, which is used in the broadcast news...
Structuring Broadcast Audio for Information Access (2003)
One rapidly expanding application area for state-of-the-art speech recognition technology is the automatic processing of broadcast audiovisual data for information access. Since much of the...
Unsupervised language model adaptation for broadcast news (2003)
Langzhou Chen, Jean-luc Gauvain, Lori Lamel, Gilles Adda
Unsupervised language model adaptation for speech recognition is challenging, particularly for complicated tasks such the transcription of broadcast news (BN) data. This paper presents an...
Feature And Score Normalization For Speaker (2003)
Verification Of Cellular, Claude Barras, Jean-luc Gauvain
This paper presents some experiments with feature and score normalization for text-independent speaker verification of cellular data. The speaker verification system is based on cepstral features and...
Structuring Broadcast Audio for Information Access (2003)
One rapidly expanding application area for state-of-the-art speech recognition technology is the automatic processing of broadcast audiovisual data for information access. Since much of the...
Structuring Broadcast Audio for Information Access (2003)
One rapidly expanding application area for state-of-the-art speech recognition technology is the automatic processing of broadcast audiovisual data for information access. Since much of the...
Automatic processing of broadcast audio in multiple languages (2002)
This paper addresses recent progress in LVCSR in multiple languages which has enabled the processing of broadcast audio for information access. At LIMSI, broadcast news transcription systems have...
The LIMSI Topic Tracking System for TDT 2002 (2002)
In this paper we describe the LIMSI topic tracking system used
Unsupervised acoustic model training (2002)
Lori Lamel, Jean-luc Gauvain, Gilles Adda
This paper describes some recent experiments using unsupervised techniques for acoustic model training in order to reduce the system development cost. The approach uses a speech recognizer to...
Connectionist language modeling for large vocabulary continuous speech recognition (2002)
Holger Schwenk, Jean-luc Gauvain
This paper describes ongoing work on a new approach for language modeling for large vocabulary continuous speech recognition. Almost all state-of-the-art systems use statistical n-gram language...
The LIMSI Broadcast News Transcription System (2002)
Jean-luc Gauvain, Lori Lamel, Gilles Adda
language modeling, lexical modeling This paper reports on activites at LIMSI over the last few years directed at the transcription of broadcast news data. We describe our development work in moving...
Transcribing Audio-Video Archives (2002)
Claude Barras, Alexandre Allauzen, Lori Lamel, Jean-luc Gauvain
This paper addresses the automatic transcription of audiovideo archives using a state-of-the-art broadcast news speech transcription system. A 9-hour corpus spanning the latter half of the 20th...
Lightly supervised and unsupervised acoustic model training (2002)
Lori Lamel, Jean-luc Gauvain, Gilles Adda
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe unrestricted broadcast news audio data with a word...
Portability issues for speech recognition technologies (2001)
Lori Lamel, Fabrice Lefevre, Jean-luc Gauvain, Gilles Adda
Although there has been regular improvement in speech recognition technology over the past decade, speech recognition is far from being a solved problem. Most recognition systems are tuned to a...
Genericity and Adaptability Issues for Task-Independent Speech Recognition (2001)
Fabrice Lefevre, Jean-luc Gauvain, Lori Lamel
The last decade has witnessed major advances in core speech recognition technology, with today's systems able to recognize continuous speech from many speakers without the need for an explicit...
Towards task-independent speech recognition (2001)
Fabrice Lefevre, Jean-luc Gauvain, Lori Lamel
Despite the considerable progress made in the last decade, speech recognition is far from a solved problem. For instance, porting a recognition system to a new task (or language) still requires...
Lori Lamel, Jean-luc Gauvain, Gilles Adda
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe broadcast audio data with a word error of about 20%....
Improving Genericity for Task-Independent Speech Recognition (2001)
Fabrice Lefevre, Jean-luc Gauvain, Lori Lamel
Although there have been regular improvements in speech recognition technology over the past decade, speech recognition is far from being a solved problem. Recognition systems are usually tuned to a...
Language model adaptation for broadcast news transcription (2001)
Langzhou Chen, Jean-luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda
This paper reports on languagemodel adaptation for the broadcast news transcription task. Language model adaptation for this task is challenging in that the subject of any particular show or portion...
The LIMSI Topic Tracking System for TDT2001 (2001)
In this paper we describe the LIMSI topic tracking system used for the DARPA 2001 Topic Detection and Tracking evaluation (TDT2001). The system relies on a unigram topic model, where the score for an...
Automatic transcription of compressed broadcast audio (2001)
Claude Barras, Lori Lamel, Jean-luc Gauvain
With increasing volumes of audio and video data broadcast over the web, it is of interest to assess the performance of state-of-theart automatic transcription systems on compressed audio data for...
The Limsi Topic Tracking System For Tdt2001 (2001)
In this paper we describe the LIMSI topic tracking system used for the DARPA 2001 Topic Detection and Tracking evaluation (TDT2001). The system relies on a unigram topic model, where the score for an...
Language-Based Multimedia Information Retrieval (2000)
Franciska Jong, Jean-luc Gauvain, Djoerd Hiemstra, Klaus Netter
for Artificial Intelligence
Considerations in the design and evaluation of spoken language dialog systems (2000)
Lori Lamel, Sophie Rosset, Jean-luc Gauvain
In this paper we summarize our experience at LIMSI in the design, development and evaluation of spoken language dialog systems for information retrieval tasks. This work has been for the most part...
Broadcast News Transcription in Mandarin (2000)
Langzhou Chen, Lori Lamel, Gilles Adda, Jean-luc Gauvain
In this paper, our work in developing a Mandarin broadcast news transcription system is described. The main focus of this work is a port of the LIMSI American English broadcast news transcription...
Fast Decoding for Indexation of Broadcast Data (2000)
Processing time is an important factor in making a speech transcription system viable for automatic indexation of radio and television broadcasts. When only concerned by the word error rate, it is...
Lightly Supervised Acoustic Model Training (2000)
Lori Lamel, Jean-luc Gauvain, Gilles Adda
Although tremendous progress has been made in speech recognition technology, with the capability of todays state-of-the-art systems to transcribe unrestricted continuous speech from broadcast data,...
The LIMSI SDR system for TREC-8 (1999)
Jean-luc Gauvain, Yannick De Kercadio, Lori Lamel, Gilles Adda
The LIMSI SDR system for TREC-8 (1999)
Jean-luc Gauvain, Yannick De Kercadio, Lori Lamel, Gilles Adda
In this paper we report on our TREC-8 SDR system, which combines an adapted version of the LIMSI 1998 Hub-4E transcription system for speech recognition with an IR system based on the Okapi term...
The LIMSI 1998 HUB-4e transcription system (1999)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Michèle Jardino
In this paper we report on our Nov98 Hub-4E system, which is an extension of our Nov97 system[4]. The LIMSI system for the November 1998 Hub-4E evaluation is a continuous mixture density, tied-state...
Recent Advances in Transcribing Television and Radio Broadcasts (1999)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Michele Jardino
Transcription of broadcast news shows (radio and television) is a major step in developing automatic tools for indexation and retrieval of the vast amounts of information generated on a daily basis....
The LIMSI 1998 HUB-4e transcription system (1999)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Michele Jardino
In this paper we report on our Nov98 Hub-4E system, which is an extension of our Nov97 system[4]. The LIMSI system for the November 1998 Hub-4E evaluation is a continuous mixture density, tied-state...
The LIMSI SDR system for TREC-8 (1999)
Jean-luc Gauvain, Yannick De Kercadio, Lori Lamel, Gilles Adda
In this paper we report on our TREC-8 SDR system, which combines an adapted version of the LIMSI 1998 Hub-4E transcription system for speech recognition with an IR system based on the Okapi term...
Partitioning and Transcription of Broadcast News Data (1998)
Jean-luc Gauvain, Lori Lamel, Gilles Adda
Radio and television broadcasts consist of a continuous stream of data comprised of segments of different linguistic and acoustic natures, which poses challenges for transcription. In this paper we...
The LIMSI 1997 Hub-4E Transcription System (1998)
Jean-luc Gauvain, Lori Lamel, Gilles Adda
In this paper we report on the LIMSI system used in the Nov'97 Hub-4E benchmark test on transcription of American English broadcast news shows. There are two main differences from the LIMSI...
The LIMSI 1997 Hub-4E Transcription System (1998)
Jean-luc Gauvain, Lori Lamel, Gilles Adda
In this paper we report on the LIMSI system used in the Nov'97 Hub-4E benchmark test on transcription of American English broadcast news shows. There are two main differences from the LIMSI...
Text normalization and speech recognition in French (1997)
Gilles Adda, Martine Adda-decker, Jean-luc Gauvain, Lori Lamel
In this paper we present a quantitative investigation into the impact of text normalization on lexica and language models for speech recognition in French. The text normalization process defines what...
Transcription Of Broadcast News (1997)
Jean-luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-decker
In this paper we report on our recent work in transcribing broadcast news shows. Radio and television broadcasts contain signal segments of various linguistic and acoustic natures. The shows contain...
Model Compensation For Noises In Training And Test Data (1997)
Driss Matrouf, Jean-luc Gauvain
It is well known that the performances of speech recognition systems degrade rapidly as the mismatch between the training and test conditions increases. Approaches to compensate for this mismatch...
Speaker Recognition With The Switchboard Corpus (1997)
In this paper we present our development work carried out in preparation for the March'96 speaker recognition test on the Switchboard corpus organized by NIST. The speaker verification system...
A Phone-based Approach to Non-Linguistic Speech Feature Identification (1995)
Contact Lori Lamel, Lori F. Lamel, Lori F. Lamel, Jean-luc Gauvain, Jean-luc Gauvain
In this paper we present a general approach to identifying non-linguistic speech features from the recorded signal using phone-based acoustic likelihoods. The basic idea is to process the unknown...
Language identification using phone-based acoustic likelihoods (1994)
Lori F. Lamel, Jean-luc Gauvain
As speech recognition technology advances, so do the aims of system designers, and the prospects of potential applications. One of the main efforts underway in the community is the development of...
Jean-luc Gauvain, Chin-hui Lee
In this paper a framework for maximum a posteriori (MAP) estimation of hidden Markov models (HMM) is presented. Three key issues of MAP estimation, namely the choice of prior distribution family, the...
Identifying non-linguistic speech features (1993)
Lori F. Lamel, Jean-luc Gauvain
Over the last decade technological advances have been made which enable us to envision real-world applications of speech technologies. It is possible to foresee applications, for example, information...
Identification of Non-Linguistic Speech Features (1993)
Jean-luc Gauvain, Lori F. Lamel
Over the last decade technological advances have been made which enable us to envision real-world applications of speech technologies. It is possible to foresee applications where the spoken query is...
Continuous Speech Recognition at LIMSI (1992)
Lori F. Lamel, Jean-luc Gauvain
This paper presents some of the recent research on speaker-independent continuous speech recognition at LIMSI including efforts in phone and word recognition for both French and English. Evaluation...
Speaker-Independent Phone Recognition Using BREF (1992)
Jean-luc Gauvain, Lori F. Lamel
A series of experiments on speaker-independent phone recognition of continuous speech have been carried out using the recently recorded BREF corpus. These experiments are the first to use this large...
Recent Activities in Spoken Language Processing at LIMSI (1992)
: This paper summarizes recent activities at LIMSI in multilingual speech recognition and its applications. While the main goal of speech recognition is to provide a transcription of the speech...
MAP Estimation of Continuous Density HMM: Theory and Applications (1992)
Jean-luc Gauvain, Chin-hui Lee
We discuss maximum a posteriori estimation of continuous density hidden Markovmodels(CDHMM).The classical MLE reestimation algorithms, namely the forward-backward algorithm and the segmental k-means...
Bayesian Learning of Gaussian Mixture Densities for Hidden Markov Models (1991)
Jean-luc Gauvain, Chin-hui Lee
An investigation into the use of Bayesian learning of the parameters of a multivariate Gaussian mixture density has been carried out. In a continuous density hidden Markov model (CDHMM) framework,...
Design Considerations and Text Selection for BREF, a large French read-speech corpus (1990)
Jean-luc Gauvain, Lori F. Lamel, Maxine Eskenazi
BREF, a large read-speech corpus in French has been designed with several aims: to provide enough speech data to develop dictation machines, to provide data for evaluation of continuous speech...
Transcribing broadcast news for audio and video indexing (0000)
The article discusses automatically keeping up-to-date with rapidly changing news broadcasts The article discusses automatically keeping up-to-date with rapidly changing news...
Transcribing broadcast news for audio and video indexing
The article discusses automatically keeping up-to-date with rapidly changing news broadcasts The article discusses automatically keeping up-to-date with rapidly changing news...
Cross-Lingual Experiments with Phone Recognition
Lori F. Lamel, Jean-luc Gauvain
This paper presents some of the recent research on speaker-independent continuous phone recognition for both French and English. The phone accuracy is assessed on the BREF corpus for French, and on...
Experiments on Speaker-Independent Phone Recognition Using BREF
Lori F. Lamel, Jean-luc Gauvain
A series of experiments for speaker-independent, continuous speech phone recognition have been carried out using the recently recorded BREF corpus. Our experiments are the first to use this database,...
BREF, a Large Vocabulary Spoken Corpus for French
Lori F. Lamel, Jean-luc Gauvain, Maxine Eskenazi
This paper presents some of the design considerations of BREF, a large read-speech corpus for French. BREF was designed to provide continuous speech data for the development of dictation machines,...