A one-pass real-time decoder using memory-efficient state network

IEICE Transactions on Information and Systems

Volumn E91-D, Issue 3, 2008, Pages 529-537

  Shao, Jian ^a   Li, Ta ^a   Zhang, Qingqing ^a   Zhao, Qingwei ^a   Yan, Yonghong ^a  

^a ThinkIT Speech Lab   (China)

Author keywords

Layer dependent beam pruning; Memory efficient; Real time

Indexed keywords

SPEECH RECOGNITION;

FORWARD-AND-BACKWARD; GARBAGE COLLECTION; LAYER-DEPENDENT BEAM PRUNING; MEMORY EFFICIENT; MEMORY REQUIREMENTS; MULTILAYER STRUCTURES; REAL TIME; SPONTANEOUS SPEECH RECOGNITION;

DECODING;

EID: 60849096562     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e91-d.3.529     Document Type: Article

References (15)

1. S. Young, N. Russel, and J. Thornton, "Token passing: A simple conceptual model for connected speech recognition systems," Techinical Report, Cambridge University, 1989.
2. H. Ney, R. Haeb-Umbach, B.H. Tran, and M. Oerder, "Improvements in beam search for 10000-word continuous speech recognition," Proc. ICASSP, vol.1, pp.9-12, 1992.
3. J.J. Odell, V. Valtchev, P.C. Woodland, and S.J. Young, "A one pass decoder design for large vocabulary recognition," Proc. DARPA Human Language Technology Workshop, pp.405-410, Plainsboro, NJ, USA, 1994.
4. J.J. Odell, The use of context in large vocabulary speech recognition, Ph.D. Thesis, University of Cambridge, Cambridge, UK, 1995.
5. M.K. Ravishankar, Efficient algorithm for speech recognition, Ph.D. Thesis, CMU, Pittsburgh, USA, 1996.
6. S. Ortmanns, H. Ney, and A. Eiden, "Language model look-ahead for large vocabulary speech recogntion," Proc. Int. Conf. Spoken Language Processing, pp.2095-2098, Philadephia, PA, USA, 1996.
7. M. Mohri and M. Riley, "Weighted determinization and minimization for large vocabulary speech recognition," Proc. EuroSpeech'97, pp.131-134, Rhodes, Greece, 1997.
8. S. Ortmanns and H. Ney, "A word graph algorithm for large vocabulary continuous speech recognition," Comput. Speech Lang., vol.11, pp.43-72, 1997.
9. J. Davenport, R. Schwartz, and L. Nguyen, "Towards a robust realtime decoder," Proc. ICASSP'99, pp.645-648, 1999.
10. H. Ney and S. Ortmanns, "Progress in dynamic programming search for LVCSR," Proc. IEEE, vol.88, no.8, 2000.
11. E. Whittaker and B. Raj, "Quantization-based language model compression," Proc. Eurospeech'01, pp.33-36, Aalborg, Denmark, 2001.
12. D. Willett, E. McDermott, Y. Minami, and S. Katagiri, "Time and memory efficient Viterbi decoding for LVCSR using a precompiled search network," Proc. Eurospeech'01, vol.2, pp.847-850, 2001.
13. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Comput. Speech Lang., vol.16, pp.69-88, 2002.
14. X.L. Aubert, "An overview of decoding techniques for large vocabulary continuous speech recognition," Comput. Speech Lang., vol.16, pp.89-114, 2002.
15. D. Povey and P.C. Woodland, "Minimum phone error and Ismoothing for improved discriminative training," Proc. ICASSP, vol.1, pp.105-108, Orlando, FL, USA, 2002.