Investigation of acoustic units for LVCSR systems

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 4872-4875

  Liu, X ^a   Gales, M J F ^a   Hieronymus, J L ^b   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELLING; AUDIO-RECOGNITION; COMPLEX PATTERN; CONTEXT DEPENDENT; ERROR RATE; IMPLICIT MODELLING; LINGUISTIC UNITS; MANDARIN CHINESE; STATISTICAL MODELS; TRAINING DATA; TRIPHONES;

LINGUISTICS; NATURAL LANGUAGE PROCESSING SYSTEMS; SIGNAL PROCESSING; SPEECH;

SPEECH COMMUNICATION;

EID: 80051623316     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947447     Document Type: Conference Paper

References (18)

1. M. Y. Chen (2000). Tone Sandhi Patterns across Chinese Dialects, Cambridge Studies in Linguistics, No. 92.
2. Y-L Chow & R. Schwartz et al. (1986). The Role of Word-Dependent Coarticulatory Effects in Phoneme-Based Speech Recognition System, in IEEE ICASSP1986.
3. C. Fuegen & I. Rogina (2000). Integrating Dynamic Speech Modalities into Context Decision Trees, in Proc. Eurospeech' 00.
4. J-L. Gauvain, L. Lamel & G. Adda (2002). The LIMSI Broadcast News Transcription System, Speech Communication, Volume 37, pp. 89-108, 2002.
5. G. Kochanski et al. (2003). Quantitative Measurement of Prosodic Strength in Mandarin, Speech Communication, Volumen 41(4), November 2003.
6. P. Ladefoged (2005). Vowels and Consonants 2nd edition, Blackwell.
7. H. Liao et al. (2010). Decision Tree Clustering withWord and Syllable Features, in Proc. Interspeech'10.
8. X. Liu, M. J. F. Gales & P. C. Woodland (2010). Language Model Cross Adaptation For LVCSR System Combination, in Proc. Interspeech'10.
9. J. Luo, L. Lamel & J-L Gauvain (2009). Modeling Characters versusWords for Mandarin Speech Recognition, in Proc. IEEE ICASSP2009.
10. M. Jones & P. C.Woodland (1994). Modelling Syllable Characteristics to Improve Large Vocabulary Continuous Speech Recognition, in Proc. IEEE ICASSP1994.
11. M. Mohri & M. Riley. Network Optimizations for Large Vocabulary Speech Recognition. Speech Communication, 25:3, 1998.
12. D. B. Paul (1991). The Lincoln Tied-Mixture HMM Continuous Speech Recognizer, in IEEE ICASSP1991.
13. J. J. Odell (1995). The Use of Context in Large Vocabulary Speech Recognition, PhD thesis, Cambridge University Engineering Department, England.
14. D. Povey & P. C. Woodland (2002). Minimum Phone Error and I-smoothing for Improved Discriminative Training, in Proc. IEEE ICASSP2002.
15. I. Shafran & M. Ostendorf (2003). Acoustic Model Clustering Based on Syllable Structure, Computer Speech and Language, 2003.
16. R. Sinha et al. (2006). The CU-HTK Mandarin broadcast news transcription system, in Proc. IEEE ICASSP2006.
17. P. C. Woodland et al. (1995). The 1994 HTK Large Vocabulary Speech Recognition System, in Proc. IEEE ICASSP1995.
18. S. J. Young, J. J. Odell & P. C. Woodland (1994). Tree-based State Tying for High Accuracy Acoustic Modeling, ARPA Human Language Age Technology Workshop, pp. 307-312, Morgan Kaufman, 1994.