Unsupervised learning of overlapped speech model parameters for multichannel speech activity detection in meetings

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

Volumn 1, Issue , 2006, Pages

  Laskowski, Kornel ^a   Schultz, Tanja ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DATA STRUCTURES; ERROR DETECTION; KNOWLEDGE ACQUISITION; PARAMETER ESTIMATION; SPEECH CODING;

MULTICHANNEL SPEECH ACTIVITY DETECTION; SPEECH ACTIVITY DETECTION SYSTEMS; SPEECH MODELS; SPEECH STATES;

SPEECH RECOGNITION;

EID: 33947615205     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. T. Pfau, D. Ellis, and A. Stolcke, "Multispeaker speech activity detecction for the icsi meeting recorder," in Proc. IEEE Automatic Speecch Recognition and Understanding Workshop, Madonna di Campiglio, Italy, 2001.
2. A. Stolcke et al, "Further progress in meeting recognition: The icsi-sri spring 2005 speech-to-text evaluation system," in Proc. NIST MLMl Meeting Recognition Workshop, Edinburgh, Scotland, July 2005, pp. 39-50.
3. S. Wrigley, G. Brown, V. Wan, and S. Renais, "Feature selection for the classification of crosstalk in multi-channel audio," in Proc. EuroSpeech, 2003.
4. S. Wrigley, G. Brown, V. Wan, and S. Renals, "Speech and crosstalk detection in multi-channel audio," in IEEE Transactions on Speech and Audio Processing, 2002.
5. K. Laskowski and T. Schultz, "Crosscorrelation-based multi-speaker speech activity detection," in Proc. ICSLP, Jeju Island, Korea, October 2004.
6. NIST, "Rich transcription," http://www.nist.gov/speech/tests/ rt/.