Duration normalization for improved recognition of spontaneous and read speech via missing feature methods

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

Volumn 1, Issue , 2001, Pages 313-316

  Nedel, Jon P ^a   Stern, Richard M ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DURATION NORMALIZATION; HIDDEN MARKOV MODEL; READ SPEECH; SPEECH RATE; SPONTANEOUS SPEECH;

FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH;

SPEECH RECOGNITION;

EID: 0034848039     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940830     Document Type: Article

References (6)

1. On the effects of speech rate in large vocabulary speech recognition systems
2. Stochastic trajectory modeling for speech recognition
3. Inference of missing spectrographic features for robust speech recognition
4. Robust automatic speech recognition with missing and unreliable acoustic data
5. Phone transition acoustic modeling: Application to speaker independent and spontaneous speech systems
6. Speech in noisy environments: Robust automatic segmentation, feature extraction, and hypothesis combination