Unsupervised Speaker Identification using Overlaid Texts in TV Broadcast
| Autor: | Poignant, Johann, Bredin, Hervé, Le, Viet-Bac, Besacier, Laurent, Barras, Claude, Quénot, Georges |
|---|---|
| Přispěvatelé: | Laboratoire d'Informatique de Grenoble (LIG), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), Vocapia Research [Orsay], Vocapia, Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF), Modélisation et Recherche d’Information Multimédia [Grenoble] (MRIM), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Saclay (COmUE), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2012 |
| Předmět: |
030507 speech-language pathology & audiology
03 medical and health sciences optical character recognition unsupervised speaker identification [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR] multimodal fusion 0202 electrical engineering electronic engineering information engineering 020206 networking & telecommunications speaker diarization reproducible results 02 engineering and technology 0305 other medical science |
| Zdroj: | Proceedings of the 13th Annual Conference of the International Speech Communication Association (Interspeech) Interspeech 2012-Conference of the International Speech Communication Association Interspeech 2012-Conference of the International Speech Communication Association, Sep 2012, Portland, OR, United States. 4p |
| Popis: | Poster Session: Speaker Recognition III; International audience; We propose an approach for unsupervised speaker identification in TV broadcast videos, by combining acoustic speaker diarization with person names obtained via video OCR from overlaid texts. Three methods for the propagation of the overlaid names to the speech turns are compared, taking into account the co-occurence duration between the speaker clusters and the names provided by the video OCR and using a task-adapted variant of the TF-IDF information retrieval coefficient. These methods were tested on the REPERE dry-run evaluation corpus, containing 3 hours of annotated videos. Our best unsupervised system reaches a F-measure of 70.2% when considering all the speakers, and 81.7% if anchor speakers are left out. By comparison, a mono-modal, supervised speaker identification system with 535 speaker models trained on matching development data and additional TV and radio data only provided a 57.5% F-measure when considering all the speakers and 45.7% without anchor. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|