Syllable-based large vocabulary continuous speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 4, 2001, Pages 358-366

  Ganapathiraju, Aravind ^b,c   Hamaker, Jonathan ^b   Picone, Joseph ^a,b   Ordowski, Mark ^a,d   Doddington, George R ^d,e  

^a IEEE   (United States)

^b MISSISSIPPI STATE UNIVERSITY   (United States)

^c Conversay ^*  (United States)

^d Department of Defense ^*  (United States)

^e NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY   (United States)

Author keywords

Acoustic modeling; Hidden Markov modeling; Speech recognition

Indexed keywords

LARGE VOCABULARY CONTINIOUS SPEECH RECOGNITION (LVCSR); WORD ERROR RATE (WER);

ACOUSTIC SIGNAL PROCESSING; BANDWIDTH; MARKOV PROCESSES; SENSORY PERCEPTION; SPEECH ANALYSIS; TELEPHONE; VOCABULARY CONTROL;

SPEECH RECOGNITION;

EID: 0035340439     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.917681     Document Type: Article

References (29)

1. SWITCHBOARD: Telephone speech corpus for research and development
2. Copernicus and the ASR challenge - Waiting for Kepler
3. Context-independent phonetic hidden Markov models for speaker-independent continuous speech recognition
4. Stochastic pronunciation modeling from hand-labeled phonetic corpora
5. Pronunciation modeling using a hand-labeled corpus for conversational speech recognition
6. Speaking in shorthand - A syllable-centric perspective for understanding pronunciation variation
7. The switchboard transcription project
8. Parameter trajectory models for speech recognition
9. Generalized mixture of HMM's for continuous speech recognition
10. From HMM's to segment models: A unified view of stochastic modeling for speech recognition
11. Modeling systematic variations in pronunciations via a language-dependent hidden speaking mode
12. Probabilistic classification of HMM states for large vocabulary continuous speech recognition
13. Syllable - A promising recognition unit for LVCSR
14. Continuous speech recognition using hidden Markov models
15. Some performance benchmarks for isolated word speech recognition systems
16. High-performance alphabet recognition
17. Speaker independent recognition of isolated words using clustering techniques
18. Performing fine phonetic distinctions: Templates vs. features
19. Isolated word recognition using a two-pass pattern recognition approach
20. Statistical segmentation and word modeling techniques in isolated word recognition
21. A probabilistic acoustic MAP based discriminative HMM training
22. A proposal for a standard partitioning of the OGI AlphaDigit corpus