A study on adapting Czech automatic speech recognition system to Croatian language

After successful adaptation of our Czech large-vocabulary speech recognition system to Slovak, we investigate the possibility to port it to another Slavic language, Croatian in this case. We describe how we build a large lexicon (recently with 255 thousand entries) and a language model from publicly available Internet sources and how an existing Czech acoustic model (AM) can be utilized for bootstrapping and training a model applicable for Croatian. For the AM adaptation we use the Croatian part of the GlobalPhone database. An independent evaluation is done on a test set made of transcribed broadcast recordings of Radio Pula. When using the original Czech acoustic model, the word error rate is 27.6%, with the model adapted to Croatian, it is reduced to 19.4%.

[1]  Daniel Povey,et al.  Large scale discriminative training of hidden Markov models for speech recognition , 2002, Comput. Speech Lang..

[2]  Jean-Luc Gauvain,et al.  Automatic Speech-to-Text Transcription in Arabic , 2009, TALIP.

[3]  Andreas G. Andreou,et al.  Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition , 1998, Speech Commun..

[4]  Ngoc Thang Vu,et al.  Rapid bootstrapping of five eastern european languages using the rapid language adaptation toolkit , 2010, INTERSPEECH.

[5]  Jan Silovský,et al.  Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio , 2011, MM4CH.

[6]  Jan Silovský,et al.  Czech-to-slovak adapted broadcast news transcription system , 2008, INTERSPEECH.

[7]  Petra Geutner,et al.  Adaptive vocabularies for transcribing multilingual broadcast news , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[8]  Jan Silovský,et al.  Challenges in Speech Processing of Slavic Languages (Case Studies in Speech Recognition of Czech and Slovak) , 2009, COST 2102 Training School.

[9]  Sanda Martinčić-Ipšić,et al.  Croatian Speech Recognition , 2010 .

[10]  Lori Lamel,et al.  Development of a speech-to-text transcription system for Finnish , 2010, SLTU.

[11]  Tanja Schultz,et al.  Globalphone: a multilingual speech and text database developed at karlsruhe university , 2002, INTERSPEECH.

[12]  Jan Silovský,et al.  Study on Cross-Lingual Adaptation of a Czech LVCSR System towards Slovak , 2010, COST 2102 Conference.

[13]  Lori Lamel,et al.  A first LVCSR system for Luxembourgish , an under-resourced European language , 2011 .

[14]  Jan Nouza,et al.  Multi-words in the Czech TV/radio News Transcription system , 2006 .

[15]  Jan Nouza,et al.  Phonetic Alphabet for Speech Recognition of Czech , 1997 .