A recognition method with parametric trajectory synthesized using direct relations between static and dynamic feature vector time series

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

Volumn 1, Issue , 2002, Pages 957-960

  Minami, Yasuhiro ^a,b   McDermott, Erik ^b   Nakamura, Atsushi ^b   Katagiri, Shigeru ^b  

^a NTT CORPORATION   (Japan)

^b NTT Communication Science Laboratories   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODEL; SPEECH TRAJECTORY;

MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY; SPEECH SYNTHESIS; VECTORS;

SPEECH RECOGNITION;

EID: 0036293703     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743952     Document Type: Article

References (10)

1. From HMMs to segment models: A unified view of stochastic modeling for speech recognition
2. Stochastic segment modeling using the estimate-maximize algorithm
3. Parametric trajectory models for speech recognition
4. Probabilistic-trajectory segmental HMMs
5. Hidden Markov models for trajectory modeling
6. Speech parameter generation from HMM using dynamic features
7. An algorithm for speech parameter generation from continuous mixture HMMs with dynamic features
8. Speech synthesis from HMMs using dynamic features
9. A recognition method using synthesis-based scoring that incorporates direct relations between static and dynamic feature vector time series
10. Spectral quantization using statistics of static and dynamic features