L. Besacier | Joseph Fourier University (original) (raw)

Papers by L. Besacier

Research paper thumbnail of ASR and Translation for UnderResourced Languages

There are more than 6000 languages in the world but only a small number possess the resources req... more There are more than 6000 languages in the world but only a small number possess the resources required for implementation of Human Language Technologies (HLT). Thus, HLT are mostly concerned by languages for which large resources are available or which have suddenly become of interest because of the economic or political scene. On the contrary, languages from developing countries or minorities have been less worked on in the past years. One way of improving this "language divide" is do more research on portability of HLT for multilingual applications.

Research paper thumbnail of The NESPOLE! speech-to-speech translation system

Proceedings of the …, Jan 1, 2002

Research paper thumbnail of The ELISA consortium approaches in speaker segmentation during the NIST 2002 speaker recognition evaluation

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., 2003

This paper presents the ELISA consortium activities in automatic speaker segmentation during last... more This paper presents the ELISA consortium activities in automatic speaker segmentation during last NIST 2002 evaluation: two different approaches from CLIPS and LIA laboratories are presented and the possibility of combining them either by applying them consecutively, or by fusing the decisions made by each of them, is investigated. Various types of data were available for NIST 2002. The ELISA systems obtained the lower error rates for two corpora: the CLIPS system obtained the best performance on the Meeting data, the LIA system obtained the best performance on the Switchboard data. The combining strategies proposed in this paper allowed us to improve the performance of the best single system on both data types (up to 30 % of error rate reduction).

Research paper thumbnail of Reconnaissance automatique de la parole pour les langues peu dotées: application au Vietnamien et au Khmer

... être ensuite remises au « pot commun » d'une langue donnée (dictionnaire phonétique,... more ... être ensuite remises au « pot commun » d'une langue donnée (dictionnaire phonétique, corpus ... du traitement des signaux complexes (parole et image), des applications multimédia et de ... Le but de ce projet est notamment d'initier au Cambodge, la création d'un nouveau groupe ...

Research paper thumbnail of {U} sing automatic speech recognition for phonological purposes:{S} tudy of {V} owel {L} enght in {P} unu ({B} antu {B} 40)

Research paper thumbnail of Autonomous acoustic model adaptation for multilingual meeting transcription involving high-and low-resourced languages

In speech technology, we found several challenges in automatic speech transcription system for mu... more In speech technology, we found several challenges in automatic speech transcription system for multilingual conferences or meetings. Firstly, the dialog occurs between native and non-native speakers. Secondly, the non-native speakers come from different parts of the world (e.g., English spoken by native French speakers or English spoken by native Vietnamese speakers, etc.). Thirdly, no data or a limited amount of data is available to bootstrap the acoustic modeling. This paper presents some autonomous online and offline acoustic model adaptation approaches, which required no additional data in the adaptation process, to deal with above challenges as well as to improve the performance of the phone recognizers used for automatic transcription purpose. Experiments show that our adaptation approach (online interpolation with MLLR based on PR-VSM) can provide about 4% absolute gain in Phone Accuracy Rate (PAR) compared to the multilingual baseline system and it is even better than the performance of the supervised monolingual systems.

Research paper thumbnail of Benefits of prior acoustic segmentation for automatic speaker segmentation

Research paper thumbnail of The ELISA consortium approaches in broadcast news speaker segmentation during the NIST 2003 rich transcription evaluation

International Conference on Acoustics, Speech, and Signal Processing, 2004

The paper presents the ELISA consortium activities in automatic speaker segmentation, also known ... more The paper presents the ELISA consortium activities in automatic speaker segmentation, also known as speaker diarization, during the NIST rich transcription (RT), 2003, evaluation. The experiments were conducted on real broadcast news data (HUB4). Two different approaches from the CLIPS and LIA laboratories are presented and different possibilities of combining them are investigated, in the framework of the ELISA consortium.

Research paper thumbnail of LIG Approach for IWSLT09: Using Multiple Morphological Segmenters for Spoken Language Translation of Arabic

Proc. of IWSLT, 2009

Abstract— This paper describes the LIG experiments in the context of IWSLT09 evaluation (Arabic t... more Abstract— This paper describes the LIG experiments in the context of IWSLT09 evaluation (Arabic to English Statistical Machine Translation task). Arabic is a morphologically rich language, and recent experimentations in our laboratory have shown that the performance of Arabic to ...

Research paper thumbnail of Multi modal verification for teleservices and security applications (M2VTS)

Proceedings IEEE International Conference on Multimedia Computing and Systems, 1999

This paper presents the European ACTS project (( MZVTS )) which stands for Multi Modal Verificati... more This paper presents the European ACTS project (( MZVTS )) which stands for Multi Modal Verification f o r Teleservices and Security Applications. The primary goal of this project is to address the issue of secured access to local and centralised services in a multimedia environment. The main objective is to extend the scope of application of networkbased services by adding novel and intelligent functionalities, enabled by automatic verification systems combining multimodal strutegies (secured access based on speech, image or other injbrmation). The objectives of the project are also to show that limitations of individual technologies (speaker verification, frontal face authentication, profile identi3cation ,...) can be overcome by relying on multi-modal decisions (combination or fusion of these technologies).

Research paper thumbnail of ASR and Translation for UnderResourced Languages

There are more than 6000 languages in the world but only a small number possess the resources req... more There are more than 6000 languages in the world but only a small number possess the resources required for implementation of Human Language Technologies (HLT). Thus, HLT are mostly concerned by languages for which large resources are available or which have suddenly become of interest because of the economic or political scene. On the contrary, languages from developing countries or minorities have been less worked on in the past years. One way of improving this "language divide" is do more research on portability of HLT for multilingual applications.

Research paper thumbnail of The NESPOLE! speech-to-speech translation system

Proceedings of the …, Jan 1, 2002

Research paper thumbnail of The ELISA consortium approaches in speaker segmentation during the NIST 2002 speaker recognition evaluation

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., 2003

This paper presents the ELISA consortium activities in automatic speaker segmentation during last... more This paper presents the ELISA consortium activities in automatic speaker segmentation during last NIST 2002 evaluation: two different approaches from CLIPS and LIA laboratories are presented and the possibility of combining them either by applying them consecutively, or by fusing the decisions made by each of them, is investigated. Various types of data were available for NIST 2002. The ELISA systems obtained the lower error rates for two corpora: the CLIPS system obtained the best performance on the Meeting data, the LIA system obtained the best performance on the Switchboard data. The combining strategies proposed in this paper allowed us to improve the performance of the best single system on both data types (up to 30 % of error rate reduction).

Research paper thumbnail of Reconnaissance automatique de la parole pour les langues peu dotées: application au Vietnamien et au Khmer

... être ensuite remises au « pot commun » d'une langue donnée (dictionnaire phonétique,... more ... être ensuite remises au « pot commun » d'une langue donnée (dictionnaire phonétique, corpus ... du traitement des signaux complexes (parole et image), des applications multimédia et de ... Le but de ce projet est notamment d'initier au Cambodge, la création d'un nouveau groupe ...

Research paper thumbnail of {U} sing automatic speech recognition for phonological purposes:{S} tudy of {V} owel {L} enght in {P} unu ({B} antu {B} 40)

Research paper thumbnail of Autonomous acoustic model adaptation for multilingual meeting transcription involving high-and low-resourced languages

In speech technology, we found several challenges in automatic speech transcription system for mu... more In speech technology, we found several challenges in automatic speech transcription system for multilingual conferences or meetings. Firstly, the dialog occurs between native and non-native speakers. Secondly, the non-native speakers come from different parts of the world (e.g., English spoken by native French speakers or English spoken by native Vietnamese speakers, etc.). Thirdly, no data or a limited amount of data is available to bootstrap the acoustic modeling. This paper presents some autonomous online and offline acoustic model adaptation approaches, which required no additional data in the adaptation process, to deal with above challenges as well as to improve the performance of the phone recognizers used for automatic transcription purpose. Experiments show that our adaptation approach (online interpolation with MLLR based on PR-VSM) can provide about 4% absolute gain in Phone Accuracy Rate (PAR) compared to the multilingual baseline system and it is even better than the performance of the supervised monolingual systems.

Research paper thumbnail of Benefits of prior acoustic segmentation for automatic speaker segmentation

Research paper thumbnail of The ELISA consortium approaches in broadcast news speaker segmentation during the NIST 2003 rich transcription evaluation

International Conference on Acoustics, Speech, and Signal Processing, 2004

The paper presents the ELISA consortium activities in automatic speaker segmentation, also known ... more The paper presents the ELISA consortium activities in automatic speaker segmentation, also known as speaker diarization, during the NIST rich transcription (RT), 2003, evaluation. The experiments were conducted on real broadcast news data (HUB4). Two different approaches from the CLIPS and LIA laboratories are presented and different possibilities of combining them are investigated, in the framework of the ELISA consortium.

Research paper thumbnail of LIG Approach for IWSLT09: Using Multiple Morphological Segmenters for Spoken Language Translation of Arabic

Proc. of IWSLT, 2009

Abstract— This paper describes the LIG experiments in the context of IWSLT09 evaluation (Arabic t... more Abstract— This paper describes the LIG experiments in the context of IWSLT09 evaluation (Arabic to English Statistical Machine Translation task). Arabic is a morphologically rich language, and recent experimentations in our laboratory have shown that the performance of Arabic to ...

Research paper thumbnail of Multi modal verification for teleservices and security applications (M2VTS)

Proceedings IEEE International Conference on Multimedia Computing and Systems, 1999

This paper presents the European ACTS project (( MZVTS )) which stands for Multi Modal Verificati... more This paper presents the European ACTS project (( MZVTS )) which stands for Multi Modal Verification f o r Teleservices and Security Applications. The primary goal of this project is to address the issue of secured access to local and centralised services in a multimedia environment. The main objective is to extend the scope of application of networkbased services by adding novel and intelligent functionalities, enabled by automatic verification systems combining multimodal strutegies (secured access based on speech, image or other injbrmation). The objectives of the project are also to show that limitations of individual technologies (speaker verification, frontal face authentication, profile identi3cation ,...) can be overcome by relying on multi-modal decisions (combination or fusion of these technologies).