Polish LVCSR in the Janus system. Preliminary results for the SpeeCon database

This paper describes the development of the LVCSR (Large Vocabulary Continuous Speech Recognition) system for Polish, using the Janus system developed at the University Karlsruhe/Carnegie Mellon University. The system has been tested on the selected material from the SpeeCon database. Test results for sentences read by 16 speakers are given. The system shows good performance and can be used as a basis for further development of modern speech recognition technology for Polish.

[1]  A. Waibel,et al.  A one-pass decoder based on polymorphic linguistic context assignment , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[2]  Alex Acero,et al.  Spoken Language Processing , 2001 .

[3]  Steve J. Young,et al.  Large vocabulary continuous speech recognition using HTK , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Richard M. Schwartz,et al.  Practical Implementations of Speaker-Adaptive Training , 1997 .

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

[6]  Einar Meister,et al.  BABEL: an Eastern European multi-language database , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[7]  Klaus Ries,et al.  The Karlsruhe-Verbmobil speech recognition engine , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Ivica Rogina,et al.  The bucket box intersection (BBI) algorithm for fast approximative evaluation of diagonal mixture Gaussians , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[9]  Renato De Mori,et al.  Spoken Dialogues with Computers , 1998 .

[10]  Ryszard Gubrynowicz,et al.  Multi-level Annotation in SpeeCon Polish Speech Database , 2004, IMTCI.

[11]  K. Marasek.  Large vocabulary continuous speech recognition system for Polish , 2003 .