National audienceAutomatic speaker segmentation and classification produce generic labels rather than the true identity of the speakers. The proposed approach is based on the use of a semantic classification tree using lexical rules to extract the true identity of the speakers from the transcription. In this paper, experiments are carried out on French broadcast news from ESTER 2005 to evaluate this approach, focusing on the impact of the various combinations of automatic vs. manual transcription with automatic vs. manual speaker segmenta-tion/classification. We also study the errors generated by the system.La segmentation et la classification automatique des locuteurs produisent des étiquettes génériques plutôt que la véritable identité de...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
International audienceIn this paper, we consider the extraction of speaker identity (first name and ...
In this paper, we consider the issue of speaker identification within audio records of broadcast new...
National audienceAutomatic speaker segmentation and classification produce generic labels rather tha...
International audienceAutomatic speaker diarization generally produces a generic label such a spkr1 ...
International audienceFor some years, processing mass of multimedia documents has become a very cruc...
International audienceThe automatic speaker diarization consists in splitting the signal into homoge...
International audienceThe automatic speaker indexing consists in splitting the signal into homogeneo...
International audienceIn this paper, we consider the extraction of speaker identity (first name and ...
Le traitement automatique de la parole est un domaine qui englobe un grand nombre de travaux : de la...
This paper describes recent studies on speaker diarization from automatic broadcast news transcripts...
La motivation de cette thèse est de développer des méthodologies et des algorithmes qui utilisent l'...
It is often important to be able to automatically label `who spoke when' during some audio data...
International audienceThis paper presents the ELISA consortium activities in automatic speaker diari...
Cette thèse traite de l’identification des locuteurs et des visages dans les journaux télévisés. L’i...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
International audienceIn this paper, we consider the extraction of speaker identity (first name and ...
In this paper, we consider the issue of speaker identification within audio records of broadcast new...
National audienceAutomatic speaker segmentation and classification produce generic labels rather tha...
International audienceAutomatic speaker diarization generally produces a generic label such a spkr1 ...
International audienceFor some years, processing mass of multimedia documents has become a very cruc...
International audienceThe automatic speaker diarization consists in splitting the signal into homoge...
International audienceThe automatic speaker indexing consists in splitting the signal into homogeneo...
International audienceIn this paper, we consider the extraction of speaker identity (first name and ...
Le traitement automatique de la parole est un domaine qui englobe un grand nombre de travaux : de la...
This paper describes recent studies on speaker diarization from automatic broadcast news transcripts...
La motivation de cette thèse est de développer des méthodologies et des algorithmes qui utilisent l'...
It is often important to be able to automatically label `who spoke when' during some audio data...
International audienceThis paper presents the ELISA consortium activities in automatic speaker diari...
Cette thèse traite de l’identification des locuteurs et des visages dans les journaux télévisés. L’i...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
International audienceIn this paper, we consider the extraction of speaker identity (first name and ...
In this paper, we consider the issue of speaker identification within audio records of broadcast new...