A segmental-feature HMM for continuous speech recognition based on a parametric trajectory model

Speech Communication

Volumn 38, Issue 1-2, 2002, Pages 115-130

  Yun, Young Sun ^a   Oh, Yung Hwan ^b  

^a Electronic Information and Communication Engineering   (South Korea)

^b Division of Computer Science   (South Korea)

Author keywords

Parametric trajectory model; Segmental HMM; Segmental feature HMM; Speech Recognition

Indexed keywords

ALGORITHMS; DATABASE SYSTEMS; FUNCTIONS; MARKOV PROCESSES; MATHEMATICAL MODELS; POLYNOMIALS; PROBABILITY; REGRESSION ANALYSIS;

HIDDEN MARKOV MODELS (HMM);

SPEECH RECOGNITION;

EID: 0036722907     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00047-4     Document Type: Article

References (15)

1. A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal
2. Speech recognition using hidden Markov models with polynomial regression functions as non-stationary states
3. Model parameter estimation for mixture density polynomial segment models
4. Speaker-independent isolated word recognition using dynamic features of speech spectrum
5. The theory of segmental hidden Markov models
6. A segmental speech model with application to word spotting
7. Parametric trajectory models for speech recognition
8. Modeling spectral dynamics for vowel classification
9. Experimental evaluation of segmental HMMs
10. Speech recognition using a linear dynamic segmental HMM
11. Probabilistic-trajectory segmental HMMs
12. Speaker-independent phone recognition using hidden Markov models
13. From HMMs to segment models: A unified view of stochastic modeling for speech recognition
14. A segmental HMM for speech pattern modeling