Towards knowledge-based features for HMM based large vocabulary automatic speech recognition

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

Volumn 1, Issue , 2002, Pages 817-820

  Launay, Benoît ^a   Siohan, Olivier ^a   Surendran, Arun ^a   Lee, Chin Hui ^b  

^a LUCENT TECHNOLOGIES   (United States)

^b NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; MEL-FREQUENCY CEPSTRAL COEFFICIENTS; VOCABULARY SPEECH RECOGNITION SYSTEM;

KNOWLEDGE BASED SYSTEMS; MARKOV PROCESSES; NEURAL NETWORKS; PROBABILITY; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 0038676761     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743864     Document Type: Article

References (14)

1. Acoustic correlates of some phonetic categories
2. Knowledge-based parameters for HMM speech recognition
3. Detecting stop consonants in continuous speech
4. Tandem acoustic modeling in large vocabulary recognition
5. Distinctive features for use in an automatic speech recognition system
6. Robust speech recognition using articulatory information
7. The geometry of phonological features
8. A decision tree state tying based on segmental clustering for acoustic modeling
9. Text-to-speech synthesis
10. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)