Analysis of low-resource acoustic model self-training

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 244-247

  Novotney, Scott ^a,b   Schwartz, Richard ^a  

^a BBN TECHNOLOGIES   (United States)

^b JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

English; Self training; Speech recognition

Indexed keywords

ACOUSTIC MODEL; LARGE VOCABULARY; PHONETIC DICTIONARY; SELF-TRAINING; UNLABELED DATA;

ACOUSTICS; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 70450189191     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. George Zavaliagkos and Thomas Colthurst, "A comparison of the data requirements of automatic speech recognition systems and human listeners", Proc. EUROSPEECH, 2582-2584, 2003
2. Ivan Bulyko, Mari Ostendorf and Andreas Stolcke, 2003. Getting more mileage from web text sources, in Proc. Of HLT/NAACL, 2003. PP. 7-9.
3. Owen Kimball, Chai-Lin Kao, Rukmini Iyer, Tresi Arvizo, and John Makhoul. 2004. Using quick transcriptions to improve conversational speech recognition, in Proc. Of International Conference on Spoken Language Processing, Jeju, Korea.
4. Lori Lamel, Jean luc Gauvain, and Gilles Adda, Lightly supervised and unsupervised acoustic model training, 2002. Computer Speech and Language, vol. 16, no. 1, PP. 115-129.
5. Jeff Ma and Rich Schwartz. 2008. Unsupervised vs. Supervised Training of Acoustic Models, in INTERSPEECH 2008, Brisbane, Australia.
6. Rohit Prasad et al., The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system, in INTERSPEECH 2005, Lisbon, Portugal. PP 1645-1648.