Progress in the CU-HTK broadcast news transcription system

@article{Gales2006ProgressIT,
  title={Progress in the CU-HTK broadcast news transcription system},
  author={Mark J. F. Gales and Do Yeong Kim and Philip C. Woodland and Ricky Ho Yin Chan and David Mrva and Rohit Sinha and Sue Tranter},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2006},
  volume={14},
  pages={1513-1525}
}
Broadcast news (BN) transcription has been a challenging research area for many years. In the last couple of years, the availability of large amounts of roughly transcribed acoustic training data and advanced model training techniques has offered the opportunity to greatly reduce the error rate on this task. This paper describes the design and performance of BN transcription systems which make use of these developments. First, the effects of using lightly supervised training data and advanced… CONTINUE READING
Highly Cited
This paper has 148 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 69 extracted citations

148 Citations

01020'06'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 148 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 45 references

CTS decoding improvements at IBM

G. Saon, D. Povey, G. Zweig
presented at the Proc. EARS STT Workshop, St. Thomas, U.S. Virgin Islands, Dec. 2003, p. XXX. • 2003
View 6 Excerpts
Highly Influenced

Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition

N. Kumar
Ph.D. dissertation, John Hopkins Univ., Baltimore, MD, 1997. • 1997
View 6 Excerpts
Highly Influenced

Development of the CU-HTK 2004 broadcast news transcription systems

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. • 2005
View 4 Excerpts
Highly Influenced

The htk book version

View 4 Excerpts
Highly Influenced