International Workshop on Spoken Language Translation (IWSLT) 2011 San Francisco, CA, USA December 8-9, 2011

The NICT ASR System for IWSLT2011

Kazuhiko Abe, Youzheng Wu, Chien-lin Huang, Paul R. Dixon, Shigeki Matsuda, Chiori Hori, Hideki Kashioka

National Institute of Information and Communication Technology, Kyoto, Japan

In this paper, we describe NICT's participation in the IWSLT 2011 evaluation campaign for the ASR Track.
   To recognize spontaneous speech, we prepared an acoustic model trained by more spontaneous speech corpora and a language model constructed with text corpora distributed by the organizer. We built the multi-pass ASR system by adapting the acoustic and language models with previous ASR results.
   The target speech was selected from talks on the TED (Technology, Entertainment, Design) program. Here, a large reduction in word error rate was obtained by the speaker adaptation of the acoustic model with MLLR. Additional improvement was achieved not only by adaptation of the language model but also by parallel usage of the baseline and speaker-dependent acoustic models. Accordingly, the final WER was reduced by 30% from the baseline ASR for the distributed test set.

Full Paper

Bibliographic reference.  Abe, Kazuhiko / Wu, Youzheng / Huang, Chien-lin / Dixon, Paul R. / Matsuda, Shigeki / Hori, Chiori / Kashioka, Hideki (2011): "The NICT ASR system for IWSLT2011", In IWSLT-2011, 28-33.