Language adaptive LVCSR through Polyphone Decision Tree Specialization

Abstract : With the distribution of speech technology products all over the world, the fast and efficient portability to new target languages be comes a practical concern. In this paper we explore the relative effectiveness of porting multilingual recognition systems to new target languages with very limited adaptation data. For this purpose we introduce a polyphone decision tree specialization method. Several recognition results are presented based on mono- and multilingual recognizers developed in the framework of the project GlobalPhone which investigates LVCSR systems in 15 languages.

[1]  Joachim Köhler.  Language adaptation of multilingual phone models for vocabulary independent speech recognition tasks , 1998, ICASSP.

[2]  S. Gokcen,et al.  A multilingual phoneme and model set: toward a universal base for automatic speech recognition , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[3]  H. Robertson,et al.  Recovery of the Kakerori: An Endangered Forest Bird of the Cook Islands , 1994 .

[4]  Paul Dalsgaard,et al.  Data-driven identification of poly- and mono-phonemes for four european languages , 1993, EUROSPEECH.

[5]  Barry Meatyard,et al.  Threatened Birds of the World , 2001 .

[6]  Kazuhiro Kondo,et al.  An evaluation of cross-language adaptation for rapid HMM development in a new language , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Edward O. Minot,et al.  Juvenile dispersion and use of habitat by the endangered Kakerori Pomarea dimidiata (Monarchinae) on Rarotonga, Cook Islands , 1995 .

[8]  Larry Gillick,et al.  Multilingual speech recognition at Dragon Systems , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[9]  Alison J. Stattersfield,et al.  Birds to watch 2 : the world list of threatened birds , 1996 .

[10]  Joachim Köhler,et al.  In-service adaptation of multilingual hidden-Markov-models , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Chalapathy Neti,et al.  Towards a universal speech recognizer for multiple languages , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[12]  Tanja Schultz,et al.  Fast bootstrapping of LVCSR systems with multilingual phoneme sets , 1997, EUROSPEECH.

[13]  Alex Waibel,et al.  The GlobalPhone Project: Multilingual LVCSR with JANUS-3 , 1997 .

[14]  Michael Finke,et al.  Wide context acoustic modeling in read vs. spontaneous speech , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[15]  J. Kohler.  Language adaptation of multilingual phone models for vocabulary independent speech recognition tasks , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[16]  Victor Zue,et al.  Multilingual spoken-language understanding in the MIT Voyager system , 1995, Speech Commun..

[17]  A. Constantinescu,et al.  On cross-language experiments and data-driven units for ALISP (Automatic Language Independent Speech Processing) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[18]  Tanja Schultz.  Adaptation of Pronunciation Dictionaries for Recognition of Unseen Languages , 1998 .

[19]  H. Robertson,et al.  Breeding biology of the Kakerori (Pomarea dimidiata) on Rarotonga, Cook Islands , 1998 .

[20]  Tanja Schultz,et al.  Multilingual and Crosslingual Speech Recognition , 1998 .