Unsupervised training on a large amount of arabic broadcast news data

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

Volumn 2, Issue , 2007, Pages

  Ma, Jeff ^a   Matsoukas, Spyros ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

Arabic broadcast news; Confidence estimation; Speech recognition; Unsupervised training

Indexed keywords

BIT ERROR RATE; DATA COMMUNICATION EQUIPMENT; FEATURE EXTRACTION; MATHEMATICAL MODELS; NEURAL NETWORKS; SPEECH RECOGNITION;

ARABIC BROADCAST NEWS; CONFIDENCE ESTIMATION; MAXIMUM MUTUAL INFORMATION (MMI); UNSUPERVISED TRAINING;

STEREOPHONIC BROADCASTING;

EID: 34547521567     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.366244     Document Type: Conference Paper

References (5)

1. J. Ma, S. Matsoukas, etc, "Unsupervised Training on Large Amounts of Broadcast News Data", ICASSP 2006, Vol. 3, pp. 1056-1059, May 2006.
2. B. Xiang, K. Nugyuen, etc. "Morphological Decomposition for Arabic Broadcast News Transcription", ICASSP 2006, Vol. 1, pp. 1089-1092, May 2006.
3. T. Hastie and R. Tibshirani. Generalized Additive Models. Chapman and Hall, London, 1990.
4. M. Siu, H. Gish, F. Richardson, "Improved estimation, evaluation and applications of confidence measures for speech recognition", Eurospeech 97.
5. http://www.nist.gov/speech/tests/ctr/h5_2000/h5-2000v1.3.htm.