Improved voice activity detection based on a smoothed statistical likelihood ratio

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

Volumn 2, Issue , 2001, Pages 737-740

  Cho, Yong Duk ^a   Al Naimi, Khaldoon ^a   Kondoz, Ahmet ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SPECTRUM ANALYSIS; SPEECH RECOGNITION; STATISTICAL METHODS;

LIKELIHOOD RATIO TEST; VOICE ACTIVITY DETECTION;

SPEECH CODING;

EID: 0034846572     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.941020     Document Type: Article

References (6)

1. A silence compression scheme for G.729 optimised for terminals conforming to ITU-T V.70
2. Voice activity detector (VAD) for adaptive multi-rate (AMR) speech teaffic channels
3. A statistical model-based voice activity detection
4. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator
5. Elimination of musical noise phonomenon with the ephraim and malah noise suppression
6. A voice activity detection employing soft decision based noise spectrum adaptation