论文信息 - Development of a speech recognition system for Spanish broadcast news

Development of a speech recognition system for Spanish broadcast news

This paper reports on the development process of a speech recognition system for Spanish broadcast news within the MESH FP6 project. The system uses the SONIC recognizer developed at the Center for Spoken Language Research (CSLR), University of Colorado. Acoustic and language models were trained using Hub4 broadcast news data. Experiments and evaluation results are reported.

Franciska de Jong | Andreea Niculescu

[1] Wen Wang,et al. Techniques for effective vocabulary selection , 2003, INTERSPEECH.

[2] John Makhoul,et al. THE 2004 BBN/LIMSI 10xRT ENGLISH BROADCAST NEWS TRANSCRIPTION SYSTEM , 2004 .

[3] Andrei Mikheev,et al. Document centered approach to text normalization , 2000, SIGIR '00.

[4] Roeland Ordelman,et al. Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition , 2007 .

[5] R. Cole,et al. Survey of the State of the Art in Human Language Technology , 2010 .

[6] Ellen M. Voorhees,et al. The TREC Spoken Document Retrieval Track: A Success Story , 2000, TREC.

[7] Sadaoki Furui. Recent Progress in Corpus-Based Spontaneous Speech Recognition , 2005, IEICE Trans. Inf. Syst..

[8] Ronald Rosenfeld,et al. Optimizing lexical and N-gram coverage via judicious use of linguistic data , 1995, EUROSPEECH.

[9] Roeland Ordelman,et al. Dutch speech recognition in multimedia information retrieval , 2003 .

[10] Lori Lamel,et al. Text normalization and speech recognition in French , 1997, EUROSPEECH.

[11] Alexandre Allauzen,et al. Where are we in transcribing French broadcast news? , 2005, INTERSPEECH.

[12] I. Bosque,et al. Gramática descriptiva de la lengua española , 1999 .