Signal modeling for high-performance robust isolated word recognition

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 6, 2001, Pages 647-654

  Karnjanadecha, M ^a   Zahorian, S A ^a  

^a Old Dominion University   (United States)

Author keywords

Cepstral analysis; Discrete cosine transforms; Feature extraction; Speech analysis; Speech recognition

Indexed keywords

COSINE TRANSFORMS; DATABASE SYSTEMS; FEATURE EXTRACTION; GAUSSIAN NOISE (ELECTRONIC); MARKOV PROCESSES; SIGNAL DISTORTION; SPECTRUM ANALYSIS;

ISOLATED WORD RECOGNITION;

SPEECH ANALYSIS;

EID: 0035441801     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.943342     Document Type: Article

References (16)

1. Speaker-independent recognition of spoken english letters
2. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
3. Fast endpoint detection algorithm for isolated word recognition in an office environment
4. On the role of spectral transition for speech perception
5. Dynamic features for segmental speech recognition
6. A comparison of several acoustic representations for speech recognition with degraded and undegraded speech
7. Robust feature extraction for alphabet recognition
8. Signal modeling for isolated word recognition
9. High-performance alphabet recognition
10. Inclusion of temporal information into features for speech recognition
11. Signal modeling techniques in speech recognition
12. Hidden Markov model toolkit V2.1 reference manual
13. A partitioned neural network approach for vowel classification using smoothed time/frequency features
14. Phone classification with segmental features and a binary-pair partitioned neural network classifier