Sciweavers

Share
ICASSP
2009
IEEE

Language model transformation applied to lightly supervised training of acoustic model for congress meetings

10 years 4 months ago
Language model transformation applied to lightly supervised training of acoustic model for congress meetings
For effective training of acoustic and language models for spontaneous speech such as meetings, it is significant to exploit the texts available in a large scale, which may not be faithful transcripts of the utterances. We have proposed a language model transformation scheme to cope with the differences between verbatim transcripts of spontaneous utterances and human-made transcripts such as those in proceedings. In this paper, we investigate its application to lightly supervised training of the acoustic model. By transforming the corresponding text in the proceedings, we can generate a very constrained model to predict the actual utterances. The experimental evaluation with the transcription system for the Japanese Congress meetings demonstrated that the proposed scheme can generate accurate labels for acoustic model training and thus realizes the comparable ASR (Automatic Speech Recognition) performance to the case using manual transcripts.
Tatsuya Kawahara, Masato Mimura, Yuka Akita
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICASSP
Authors Tatsuya Kawahara, Masato Mimura, Yuka Akita
Comments (0)
books