Podcastle: collaborative training of acoustic models on the basis of wisdom of crowds for podcast transcription

This paper presents acoustic-model-training techniques for improving automatic transcription of podcasts. A typical approach for acoustic modeling is to create a task-specific corpus including hundreds (or even thousands) of hours of speech data and their accurate transcriptions. This approach, however, is impractical in podcast-transcription task because manual generation of the transcriptions of the large amounts of speech covering all the various types of podcast contents will be too costly and time consuming. To solve this problem, we introduce collaborative training of acoustic models on the basis of wisdom of crowds, i.e., the transcriptions of podcast-speech data are generated by anonymous users on our web service PodCastle. We then describe a podcast-dependent acoustic modeling system by using RSS metadata to deal with the differences of acoustic conditions in podcast speech data. From our experimental results on actual podcast speech data, the effectiveness of the proposed acoustic model training was confirmed.

[1]  Chin-Hui Lee,et al.  Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains , 1994, IEEE Trans. Speech Audio Process..

[2]  Thomas Hain,et al.  Recognition and understanding of meetings the AMI and AMIDA projects , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[3]  Tatsuya Kawahara.  Benchmark test for speech recognition using the Corpus of Spontaneous Japanese , 2003 .

[4]  Masataka Goto,et al.  Speech repair: quick error correction just by using selection operation for speech input interfaces , 2005, INTERSPEECH.

[5]  Richard M. Schwartz,et al.  BBN at TREC7: Using Hidden Markov Models for Information Retrieval , 1998, TREC.

[6]  Junta Mizuno,et al.  A similar content retrieval method for podcast episodes , 2008, 2008 IEEE Spoken Language Technology Workshop.

[7]  Masataka Goto,et al.  Automatic transcription for a web 2.0 service to search podcasts , 2007, INTERSPEECH.

[8]  Andreas Stolcke,et al.  Finding consensus in speech recognition: word error minimization and other applications of confusion networks , 2000, Comput. Speech Lang..

[9]  David Watt.  Recognition and Understanding , 1996 .

[10]  Masataka Goto,et al.  Development of the RWC Music Database , 2004 .

[11]  Philip C. Woodland,et al.  Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models , 1995, Comput. Speech Lang..

[12]  Olivier Galibert,et al.  The LIMSI 2006 TC-STAR EPPS Transcription Systems , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[13]  Masataka Goto,et al.  Podcastle: a web 2.0 approach to speech recognition research , 2007, INTERSPEECH.

[14]  Beth Logan,et al.  Speechbot: an experimental speech-based search engine for multimedia content on the web , 2002, IEEE Trans. Multim..

[15]  Peter Beyerlein,et al.  Speaker adaptation in the Philips system for large vocabulary continuous speech recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  James R. Glass,et al.  Recent progress in the MIT spoken lecture processing project , 2007, INTERSPEECH.