Use of voicing features in HMM-based speech recognition

Speech Communication

Volumn 37, Issue 3-4, 2002, Pages 197-211

  Thomson, David L ^a   Chengalvarayan, R ^a  

^a NOKIA RESEARCH CENTER   (United States)

Author keywords

Autocorrelation function; Cepstral mean subtraction; Discriminative training; Hidden Markov models; Hierarchical signal bias removal; Jitter; Periodicity; Speech recognition features; Voiced and unvoiced speech; Voicing

Indexed keywords

CORRELATION METHODS; ERROR ANALYSIS; FUNCTIONS; JITTER; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH CODING; SPEECH COMMUNICATION;

AUTOCORRELATION FUNCTIONS; MINIMUM STRING ERROR (MSE);

SPEECH RECOGNITION;

EID: 0036642777     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00011-5     Document Type: Article

References (29)

1. A pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition
2. Discriminative feature selection for speech recognition
3. Subband based speech recognition
4. Is ASR ready for wireless primetime: Measuring the core technology for selected applications
5. On the use of normalized LPC error towards better large-vocabulary speech recognition systems
6. Signal conditioned minimum error rate training
7. Towards robust speech recognition in the telephony network environment: Cellular and landline conditions
8. Recent advances in robust speech recognition
9. High-accuracy connected digit recognition for mobile applications
10. Pitch as a voicing cue
11. Robust speaker-independent word recognition using static, dynamic and acceleration features: Experiments with Lombard and noisy speech
12. A comparison of signal processing frontends for automatic word recognition
13. The segmental k-means algorithm for estimating parameters of hidden Markov models
14. Minimum classification error rate methods for speech recognition
15. Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method
16. Spectral characterization of jitter, shimmer, and additive noise in synthetically generated voice signals
17. Fast and accurate pitch detection using pattern recognition and adaptive time-domain analysis
18. A tutorial on hidden Markov models and selected applications in speech recognition
19. Recognition of isolated-digits using hidden Markov models with continuous mixture densities
20. Signal conditioning techniques for robust speech recognition
21. A pitch determination and voiced/unvoiced decision algorithm for noisy speech
22. Predictable and random components of jitter
23. A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition
24. Vocabulary independent discriminative utterance verification for nonkeyword rejection in subword-based speech recognition
25. Ten case studies of the effect of field conditions on speech recognition error
26. Use of periodicity and jitter as speech recognition features
27. Lattice-based discriminative training for large vocabulary speech recognition