The development of the HTK Broadcast News transcription system: An overview

Speech Communication

Volumn 37, Issue 1-2, 2002, Pages 47-67

  Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Broadcast news transcription; Large vocabulary speech recognition

Indexed keywords

AUDIO ACOUSTICS; BIT ERROR RATE; DECODING; MATHEMATICAL MODELS; REAL TIME SYSTEMS; SPEECH RECOGNITION;

BROADCAST NEWS TRANSCRIPTION SYSTEMS;

RADIO BROADCASTING;

EID: 0036567794     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00059-0     Document Type: Article

References (38)

1. A compact model for speaker adaptive training
2. Text-free speaker recognition using an arithmetic harmonic sphericity measure
3. A post-processing system to yield reduced word error rates: Recogniser Output Voting Error Reduction (ROVER)
4. Maximum likelihood linear transformations for HMM-based speech recognition
5. Mean and variance adaptation within the MLLR framework
6. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
7. Transcription of broadcast news
8. An overview of Broadcast News corpora
9. Segment generation and clustering in the HTK Broadcast News Transcription System
10. The 1998 HTK system for transcription of conversational telephone speech
11. Perceptual linear prediction (PLP) analysis for speech
12. Spoken document retrieval for TREC-8 at Cambridge University
13. Estimation of probabilities from sparse data for the language model component of a speech recogniser
14. Improved clustering techniques for class-based statistical language modelling
15. Advances in transcription of broadcast news
16. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
17. Flexible speaker adaptation using maximum likelihood linear regression
18. Algorithms for bigram and trigram clustering
19. Comparison of part-of-speech and automatically derived category-based language models for speech recognition
20. A one pass decoder design for large vocabulary recognition
21. The 1998 CUHTK-entropic 10 × RT broadcast news transcription system
22. The role of the National Institute of Standards and Technology in DARPA's Broadcast News continuous speech recognition research program
23. 1997 Broadcast news benchmark test results: English and non-English
24. Experiments in speaker normalisation and adaptation for large vocabulary speech recognition
25. Automatic segmentation, classification and clustering of broadcast news data
26. The Cambridge University multimedia document retrieval demo system
27. Dragon Systems' 1997 broadcast news transcription system
28. Large scale discriminative training for speech recognition
29. Large vocabulary continuous speech recognition using HTK
30. The 1994 HTK large vocabulary speech recognition system
31. The HTK large vocabulary recognition system for the 1995 ARPA H3 task
32. Iterative unsupervised adaptation using maximum likelihood linear regression
33. The development of the 1996 broadcast news transcription system
34. Broadcast news transcription using HTK
35. The 1997 HTK broadcast news transcription system
36. The 1998 HTK broadcast news transcription system: Development and results
37. Tree-based state tying for high accuracy acoustic modelling