论文信息 - SHoUT, the university of twente submission to the n-best 2008 speech recognition evaluation for dutch

SHoUT, the university of twente submission to the n-best 2008 speech recognition evaluation for dutch

In this paper we present our primary submission to the first Dutch and Flemish large vocabulary continuous speech recognition benchmark, N-Best. We describe our system workflow, the models we created for the four evaluation tasks and how we approached the problem of compounding that is typical for a language such as Dutch. We present the evaluation results and our post-evaluation analysis.

Franciska de Jong | Roeland Ordelman | Marijn Huijbregts | Laurens van der Werff

[1] Nelleke Oostdijk,et al. The Spoken Dutch Corpus. Overview and First Evaluation , 2000, LREC.

[2] Chin-Hui Lee,et al. Structural maximum a posteriori linear regression for fast HMM adaptation , 2002, Comput. Speech Lang..

[3] Andreas Stolcke,et al. SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[4] David A. van Leeuwen,et al. N-best: the northern- and southern-dutch benchmark evaluation of speech recognition technology , 2007, INTERSPEECH.

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

[6] David A. van Leeuwen,et al. The AMI Speaker Diarization System for NIST RT06s Meeting Data , 2006, MLMI.

[7] Marijn Huijbregts,et al. The blame game: performance analysis of speaker diarization system components , 2007, INTERSPEECH.

[8] Roeland Ordelman,et al. Filtering the unknown: speech activity detection in heterogeneous video collections , 2007, INTERSPEECH.

[9] Steve Young,et al. Token passing: a simple conceptual model for connected speech recognition systems , 1989 .

[10] Franciska de Jong,et al. Fast n-gram language model look-ahead for decoders with static pronunciation prefix trees , 2008, INTERSPEECH.