Automatic transcription of Broadcast News

Speech Communication

Volumn 37, Issue 1-2, 2002, Pages 69-87

  Chen, S S ^a   Eide, E ^a   Gales, M J F ^a   Gopinath, R A ^a   Kanvesky, D ^a   Olsen, P ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Acoustic modeling; Adaptive training; Broadcast news; Model selection; Segmentation and clustering; Speech recognition

Indexed keywords

ALGORITHMS; AUDIO ACOUSTICS; MATHEMATICAL MODELS;

BROADCASTING NEWS (BN) TRANSCRIPTION;

RADIO BROADCASTING;

EID: 0036567784     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00060-7     Document Type: Article

References (31)

1. A compact model for speaker-adaptive training
2. Robust methods for using context-dependent features and models in a continuous speech recognizer
3. Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task
4. Transcription of BN Shows with the IBM LVCSR system
5. Transcription of broadcast news shows with the IBM large vocabulary speech recognition system
6. Speaker, channel and environment change detection
7. Class-based n-gram models of natural language
8. Robust parametric modelling of durations in hidden Markov models
9. Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news
10. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (rover)
11. Maximum likelihood linear transformations for HMM-based speech recognition
12. Cluster adaptive training for speech recognition
13. Semi-tied covariance matrices for hidden Markov models
14. Text-independent speaker identification
15. Maximum likelihood modeling with Gaussian distributions for classification
16. Automatic speaker clustering
17. The 1996 BBN Byblos Hub-4 transcription system
18. Maximum likelihood estimation for multivariate observations of Markov sources
19. Overview of the 1997 DARPA speech recognition workshop
20. Modelling of continuous speech observations
21. Estimating the dimension of a model
22. Automatic segmentation, classification and clustering of broadcast news audio
23. Best-first model merging for hidden Markov model induction
24. On the law of frequency of errors
25. An improved segmentation and clustering scheme using the Bayesian Information Criterion
26. The Development of the 1996 HTK broadcast news transcription system