DySANA: Dynamic Speech and Noise Adaptation for voice activity detection

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 127-130

  Weiss, Ron J ^a   Kristjansson, Trausti ^b  

^a Och Spine at New York Presbyterian Hospitals   (United States)

^b GOOGLE INC   (United States)

Author keywords

Endpointing; Kalman filter; Lombard effect; Voice activity detection

Indexed keywords

CONTINUITY CONSTRAINTS; DYNAMIC DISTRIBUTION; ENDPOINTING; LOMBARD EFFECT; NOISE ADAPTATION; RATE OF CHANGE; SIGNAL LEVEL; SPEECH ENDPOINT DETECTION; STATE TRANSITION MATRIX; VOCAL INTENSITY; VOICE ACTIVITY DETECTION;

ENCODING (SYMBOLS); KALMAN FILTERS; SIGNAL DETECTION; SIGNAL TO NOISE RATIO; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 84867225559     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. "ANSI-C code for the adaptive multi rate (AMR) speech codec," June 2007, 3GPP standard document. 3GPP TS 26.073 V7.0.0.
2. S. Rennie, T. Kristjansson, P. Olsen, and R. Gopinath, "Dynamic noise adaptation," in Proceedings of ICASSP, 2006.
3. M. Fujimoto and K. Ishizuka, "Noise robust voice activity detection based on switching Kalman filter," in Proceedings of Interspeech, 2007, pp. 2933-2936.
4. K.Murphy, "Switching Kalman filters," U. C. Berkeley, Tech. Rep., 1998.
5. H.-G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in ASR-2000, 2000, pp. 181-188.
6. "Speech processing, transmission and quality aspects (STQ), distributed speech recognition, advanced front-end feature extraction algorithm, compression algorithms," 2007, eTSI standard document. ETSI ES 202 050 V1.1.5.