Incorporating Named Entity Recognition into the Speech Transcription Process

Abstract : Named Entity Recognition (NER) from speech usually involves two sequential steps: transcribing the speech using Automatic Speech Recognition (ASR) and annotating the outputs of the ASR process using NER techniques. Recognizing named entities in automatic transcripts is difficult due to the presence of transcription errors and the absence of some important NER clues, such as capitalization and punctuation. In this paper, we describe a methodology for speech NER which consists of incorporating NER into the ASR process so that the ASR system generates transcripts annotated with named entities. The combination is achieved by adapting ASR language models and pre-annotating the pronunciation dictionary. We evaluate this method on ESTER 2 corpus, and show significant improvements over traditional approaches.
Type de document :
Communication dans un congrès
Interspeech, 2013, Lyon, France. Interspeech 2013, 2013
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01433438
Contributeur : Sylvain Meignier <>
Soumis le : samedi 1 avril 2017 - 00:56:50
Dernière modification le : jeudi 5 avril 2018 - 10:36:49
Document(s) archivé(s) le : dimanche 2 juillet 2017 - 12:14:30

Fichier

i13_3732.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01433438, version 1

Citation

Mohamed Hatmi, Christine Jacquin, Emmanuel Morin, Sylvain Meignier. Incorporating Named Entity Recognition into the Speech Transcription Process. Interspeech, 2013, Lyon, France. Interspeech 2013, 2013. 〈hal-01433438〉

Partager

Métriques

Consultations de la notice

284

Téléchargements de fichiers

34