[Univ of Cambridge] [Dept of Engineering]

HTK Rich Audio Transcription
References




References

Full Papers [back to top]

# FILES Details
P33.
K. C. Sim & M. J. F. Gales
Temporally Varying Model Parameters for Large Vocabulary Continuous Speech Recognition
To appear, Eurospeech 2005, September 2005 (Lisbon, Portugal)
P32. ps
pdf
html
R. Sinha, S. E. Tranter, M. J. F. Gales & P. C. Woodland
The Cambridge University March 2005 Speaker Diarisation System
To appear, Eurospeech 2005, September 2005 (Lisbon, Portugal)
P31.   M. J. F. Gales, B. Jia, X. Liu, K. C. Sim, P. C. Woodland & K. Yu
Development of the CUHTK 2004 RT04F Mandarin Conversational Telephone Speech Transcription System
Proc. ICASSP 2005, Volume I, pp. 841-844, March 2005 (Philadelphia, PA)
P30. abstract
Y. Liu, E. Shriberg, A. Stolcke, B. Peskin, J. Ang, D. Hillard, M. Ostendorf, M. Tomalin, P.C. Woodland and M. Harper
Structural Metadata Research in the EARS Program
Proc. ICASSP 2005, Volume V, pp. 957--960, March 2005 (Philadelphia, PA)
P29. abstract
pdf
ps
html
S. E. Tranter
Two-way Cluster Voting to Improve Speaker Diarisation Performance
Proc. ICASSP 2005, Volume I, pp. 753-756, March 2005 (Philadelphia, PA)
P28. abstract
pdf
ps
D. Y. Kim, H. Y. Chan, G. Evermann, M. J. F. Gales, D. Mrva, K. C. Sim & P. C. Woodland
Development of the CU-HTK 2004 Broadcast News Transcription Systems
Proc. ICASSP 2005, Volume I, pp. 861-864, March 2005 (Philadelphia, PA)
P27.   G. Evermann, H. Y. Chan, M. J. F. Gales, B. Jia, D. Mrva, P.C. Woodland & K. Yu
Training LVCSR systems on thousands of hours of data
Proc. ICASSP 2005, Volume I, pp. 209-212, March 2005 (Philadelphia, PA)
P26. abstract
pdf
ps
X. Liu, M. J. F. Gales, K. C. Sim & K. Yu
Investigation of Acoustic Modeling Techniques for LVCSR Systems
Proc. ICASSP 2005, Volume I, pp. 849-852, March 2005 (Philadelphia, PA)
P25. abstract
pdf
ps
K. C. Sim & M. J. F. Gales
Adaptation of Precision Matrix Models on Large Vocabulary Continuous Speech Recognition
Proc. ICASSP 2005, Volume I, pp. 97-100, March 2005 (Philadelphia, PA)
P24. abstract
pdf
ps
html
S. E. Tranter, M. J. F. Gales, R. Sinha, S. Umesh & P. C. Woodland
The Development of the Cambridge University RT-04 Diarisation System
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P23. abstract
pdf
ps
M. Tomalin & P. C. Woodland
The RT04 Evaluation Structural Metadata Systems at CUED
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P22. D. Y. Kim, H. Y. Chan, G. Evermann, M. J. F. Gales, D. Mrva, K. C. Sim & P. C. Woodland
Recent Developments at Cambridge in Broadcast News Transcription
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P21. M. J. F. Gales, B. Jia, X. Liu, K. C. Sim, P. C. Woodland & K. Yu
Development of the CUHTK 2004 RT04F Mandarin Conversational Telephone Speech Transcription System
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P20. abstract
pdf
ps
M. J. F. Gales, X. Liu, K. C. Sim & K. Yu
Investigation of Acoustic Modeling Techniques for LVCSR Systems
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P19. G. Evermann, H. Y. Chan, M. J. F. Gales, B. Jia, X. Liu, D. Mrva, K. C. Sim, L. Wang, P. C. Woodland & K. Yu
Development of the 2004 CU-HTK English CTS Systems Using More Than Two Thousand Hours of Data
Proc. Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
P18. abstract
pdf
ps
D. Y. Kim, S. Umesh, M. J. F. Gales, T. Hain & P. C. Woodland
Using VTLN for Broadcast News Transcription
Proc. ICSLP 2004, October 2004 (Jeju Island, Korea)
P17. abstract
pdf
ps
D. Mrva & P. C. Woodland
A PLSA-based Language Model for Conversational Telephone Speech
Proc. ICSLP 2004, October 2004 (Jeju Island, Korea)
P16. abstract
pdf
ps
S. E. Tranter
Cluster Voting for Speaker Diarisation
Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-476. May 2004
P15. abstract
pdf
ps
html
S. E. Tranter & D. A. Reynolds
Speaker Diarisation for Broadcast News
Proc. Odyssey 2004 Speaker and Language Recognition Workshop, pp. 337-344, June 2004 (Toledo, Spain)
P14. abstract
pdf
ps
K. Yu & M.J.F. Gales
Adaptive Training using Structured Transforms
Proc. ICASSP 2004, Vol I, pp. 317-320, May 2004 (Montreal, Canada)
P13. abstract
pdf
ps
X. Liu & M.J.F. Gales
Model Complexity Control and Compression using Discriminative Growth Functions
Proc. ICASSP 2004, Vol. I, pp. 797-800, May 2004 (Montreal, Canada)
P12. abstract
pdf
ps
K.C. Sim & M.J.F. Gales
Basis Superposition Precision Matrix Modelling For Large Vocabulary Continuous Speech Recognition
Proc. ICASSP 2004, Vol I, pp. 801-804, May 2004 (Montreal, Canada)
P11. abstract
pdf
ps
L. Wang & P.C. Woodland
MPE-based Discriminative Linear Transform For Speaker Adaptation
Proc. ICASSP 2004, Vol I, pp. 321-324, May 2004 (Montreal, Canada)
P10. abstract
pdf
ps
H.Y. Chan & P.C. Woodland
Improving Broadcast News Transcription by Lightly Supervised Discriminative Training
Proc. ICASSP 2004, Vol I, pp. 737-740, May 2004 (Montreal, Canada)
P9. abstract
pdf
ps
G. Evermann, H.Y. Chan, M.J.F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang & P.C. Woodland
Development of the 2003 CU-HTK Conversational Telephone Speech Transcription System
Proc. ICASSP 2004, Vol I, pp. 249-252, May 2004 (Montreal, Canada)
P8. abstract
pdf
ps
html
S. E. Tranter, K. Yu, G. Evermann & P. C. Woodland
Generating and Evaluating Segmentations for Automatic Speech Recognition of Conversational Telephone Speech
Proc. ICASSP 2004, Vol I, pp. 753-756, May 2004 (Montreal, Canada)
P7. abstract
pdf
ps
T. Hain, P. C. Woodland, G. Evermann, X. Liu, G. L. Moore, D. Povey & L. Wang
Automatic Transcription of Conversational Telephone Speech. Development of the CU-HTK 2002 System
Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-465. December 2003
P6. abstract
pdf
ps
X. Liu & M. J. F. Gales
Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions
Proc. ASRU 2003, pp. 37-42, December 2003 (St Thomas, US Virgin Islands)
P5. abstract
pdf
ps
D. Y. Kim, G. Evermann, T. Hain, D. Mrva, S. E. Tranter, L. Wang & P. C. Woodland
Recent Advances in Broadcast News Transcription
Proc. ASRU 2003, pp. 105-110, December 2003 (St Thomas, US Virgin Islands)
P4. abstract
pdf
ps
L. Wang & P. C. Woodland
Discriminative Adaptive Training Using The MPE criterion
Proc. ASRU 2003, pp. 279-284, December 2003 (St Thomas, US Virgin Islands)
P3. abstract
pdf
ps
G. Evermann & P. C. Woodland
Design of Fast LVCSR Systems
Proc. ASRU 2003, pp. 7-12, December 2003 (St Thomas, US Virgin Islands)
P2. abstract
pdf
ps
S. E. Tranter, K. Yu, D. A. Reynolds, G. Evermann, D. Y. Kim & P. C. Woodland
An Investigation into the Interactions between Speaker Diarisation Systems and Automatic Speech Transcription
Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-464. October 2003
P1. abstract
pdf
ps
X. Liu, M. J. F. Gales & P. C. Woodland
Automatic Complexity Control for HLDA Systems
Proc. ICASSP 2003, April 2003 (Hong Kong)

Workshop Slides [back to top]

# FILES Details
W38. Slides:
pdf
2up-ps
K.C. Sim, M. J. F. Gales, X. Liu, P. C. Woodland & K. Yu
Progress in English Conversational Telephone Speech Transcription
STT Technical Meeting, March 2005 (Philadelphia, PA)
W37. Slides:
pdf
2up-ps
D. Y. Kim, M. J. F. Gales & P. C. Woodland
BN-E Experiments in Cambridge
STT Technical Meeting, March 2005 (Philadelphia, PA)
W36. Slides:
pdf
2up-ps
M. Tomalin & P.C. Woodland
Recent improvements in the CUED CTS SU system
MDE Technical Meeting, March 2005 (Philadelphia, PA)
W35. Slides:
pdf
2up-ps
S.E. Tranter, R. Sinha, M.J.F. Gales, & P.C. Woodland
Recent Improvements in the CUED Diarisation System
MDE Technical Meeting, March 2005 (Philadelphia, PA)
W34. Slides:
M.J.F. Gales, B. Jia, X. Liu, K.C. Sim, P. C. Woodland & K. Yu
CU-HTK RT04f Mandarin CTS System
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W33. Slides:
M.J.F. Gales, X. Liu, K.C. Sim & K. Yu
Acoustic Modelling Techniques for LVCSR
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W32. Slides:
G. Evermann, H.Y. Chan, M.J.F. Gales, B. Jia, D. Mrva, P. C. Woodland & K. Yu
Large-Scale LVCSR Model Training on Fisher Data
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W31. Slides:
pdf
2up-ps
M. Tomalin, S.E. Tranter, M.J.F. Gales, R. Sinha, S. Umesh & P. C. Woodland
RT-04 MDE Evaluation Systems at CUED
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W30. Slides:
pdf
2up-ps
M. Tomalin & P. C. Woodland
Advances in Structural Metadata for RT-04 at CUED
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W29. Slides:
pdf
2up-ps
S. E. Tranter, M. J. F. Gales, R. Sinha, S. Umesh & P. C. Woodland
The Development of the Cambridge University RT-04 Diarisation System
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W28. Slides:
pdf
2up-ps
D.Y. Kim, H.Y. Chan, G. Evermann, M.J.F. Gales, D. Mrva, K.C. Sim & P.C. Woodland
Recent Developments at Cambridge in Broadcast News Transcription
Fall 2004 Rich Transcription Workshop (RT-04f), November 2004 (Palisades, NY)
W27. Slides:
pdf
2up-ps
H.Y. Chan, M.J.F. Gales & P.C. Woodland
Ongoing Experiments with Lightly Supervised Discriminative Training
EARS STT Technical Meeting, May 2004 (Montreal, Canada).
W26. Slides:
pdf
2up-ps
K.C. Sim & M.J.F. Gales
Precision Matrix Modelling for LVCSR
EARS STT Technical Meeting, May 2004 (Montreal, Canada).
W25. Slides:
pdf
2up-ps
D.Y. Kim, M.J.F. Gales, H.Y.Chan, P.C. Woodland, S. Umesh & T. Hain
Progress in Broadcast News English Transcription
EARS STT Technical Meeting, May 2004 (Montreal, Canada).
W24. Slides:
pdf
2up-ps
G. Evermann, B. Jia, K. Yu, D. Mrva, H.Y. Chan, M.J.F. Gales & P.C. Woodland
Experiments with Fisher Data
EARS STT Technical Meeting, May 2004 (Montreal, Canada).
W23. Slides:
pdf
2up-ps
S.E. Tranter & S. Umesh
Diarisation Research at CUED
EARS MDE Technical Meeting, May 2004 (Boston, MA).
W22. Slides:
pdf
2up-ps
M. Tomalin & P.C. Woodland
Advances in Structural Metadata at CUED
EARS MDE Technical Meeting, May 2004 (Boston, MA).
W21. Slides:
pdf
2up-ps
P.C. Woodland
EARS STT Overview
EARS Mid-year Meeting, Feb 2004 (Vienna, VA).
W20. Slides:
pdf
2up-ps
P.C. Woodland, H.Y. Chan, G. Evermann, M.J.F. Gales, T. Hain, B. Jia, D.-Y. Kim, X. Liu, D. Mrva, K.C. Sim, S.E. Tranter & L. Wang
Cambridge STT Overview
EARS Mid-year Meeting, Feb 2004 (Vienna, VA).
W19. Slides:
pdf
2up-ps
M. Tomalin, S.E. Tranter & P.C. Woodland
Metadata at CUED: Progress, Plans, and Issues
EARS Mid-year Meeting, Feb 2004 (Vienna, VA).
W18. Slides:
pdf
G. Evermann
Optimising Fast LVCSR systems
EARS STT Technical Meeting, Dec 2003 (St Thomas, US Virgin Islands).
W17. Slides:
pdf
K. Yu & M. J. F. Gales
Adaptive Training with Structured Transforms
EARS STT Technical Meeting, Dec 2003 (St Thomas, US Virgin Islands).
W16. Slides:
pdf
L. Wang & P. C. Woodland
Discriminative Adaptation and Adaptive Training
EARS STT Technical Meeting, Dec 2003 (St Thomas, US Virgin Islands).
W15. Slides:
pdf
H. Y. Chan, G. Evermann, B. Jia, D. Mrva & P. C. Woodland
Ongoing Experiments with Fisher Data
EARS STT Technical Meeting, Dec 2003 (St Thomas, US Virgin Islands).
W14. Slides:
pdf
2up-ps
M. Tomalin, S. E. Tranter & P. C. Woodland
SU Detection for RT-03f at Cambridge University.
RT-03f Workshop, November 2003 (Washington, DC).
W13. Slides:
pdf
2up-ps
T. Hain
Single Pronunciation Dictionaries - Construction and Performance
EARS STT Technical Meeting, Sept 2003 (Martigny, Switzerland).
W12. Slides:
pdf
2up-ps
X. Liu & M. J. F. Gales
Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions
EARS STT Technical Meeting, Sept 2003 (Martigny, Switzerland).
W11. Slides:
pdf
2up-ps
H. Y. Chan & P. C. Woodland
Experiments with lightly supervised discriminative training on TDT data
EARS STT Technical Meeting, Sept 2003 (Martigny, Switzerland).
W10. Slides:
pdf
ps
P. C. Woodland & H. Y. Chan
Some Results on CTS Quick Transcription and Fisher Data
EARS STT Technical Meeting, Sept 2003 (Martigny, Switzerland).
W9. Slides:
pdf
2up-ps
M. Tomalin, S. E. Tranter, P. C. Woodland and the CUED STT Team (including J.-H. Kim)
Structural Metadata at CUED: Progress Report.
EARS meeting, May 2003 (Boston, MA).
W8. Slides:
pdf
2up-ps
S. E. Tranter, K. Yu, D. A. Reynolds, D. Y. Kim, G. Evermann, P. C. Woodland and the HTK STT team
Interactions Between Diarisation and STT.
RT-03s workshop, May 2003 (Boston, MA).
W7. Slides:
pdf
2up-ps
S. E. Tranter, K. Yu and the HTK STT team
Diarisation for RT-03s at Cambridge University.
RT-03s workshop, May 2003 (Boston, MA).
W6. Slides:
pdf
2up-ps
B. Jia, K. C. Sim, M. J. F. Gales, T. Hain, X. Liu, P. C. Woodland, K. Yu and the HTK STT Team
CU-HTK RT-03 Mandarin CTS System.
RT-03s workshop, May 2003 (Boston, MA).
W5. Slides:
pdf
2up-ps
P. C. Woodland, H. Y. Chan, G. Evermann, M. J. F. Gales, T. Hain, D. Y. Kim, X. Liu, D. Mrva, D. Povey, S. E. Tranter, L. Wang & K. Yu
2003 CU-HTK English CTS System.
RT-03s workshop, May 2003 (Boston, MA).
W4. Slides:
pdf
2up-ps
D. Y. Kim, G. Evermann, T. Hain, D. Mrva, S. E. Tranter, L. Wang & P. C. Woodland
2003 CU-HTK Broadcast News English System Development.
RT-03s workshop, May 2003 (Boston, MA).
W3. Slides:
pdf
2up-ps
G. Evermann, D. Y. Kim, L. Wang, P. C. Woodland and the rest of the HTK STT team
2003 CU-HTK Fast System Description.
RT-03s workshop, May 2003 (Boston, MA).
W2. Slides:
pdf
2up-ps
P. C. Woodland, G. Evermann, M. J. F. Gales, T. Hain, H. Y. Chan, B. Jia, D. Y. Kim, X. Liu, D. Mrva, D. Povey, K. C. Sim, M. Tomalin, S. E. Tranter, L. Wang & K. Yu
Recent Experiments with HTK Broadcast News and Conversational Telephone Systems.
EARS Mid-year meeting, January 2003 (Berkeley, CA).
W1. Slides:
pdf
2up-ps
S. E. Tranter, M. Tomalin, K. Yu and the HTK STT Team
Metadata Extraction at Cambridge University.
EARS Mid-year meeting, January 2003 (Berkeley, CA).
W0. Slides:
abstract
pdf
ps
P. C. Woodland, G. Evermann, M. J. F. Gales, T. Hain, X. Liu, G. L. Moore, D. Povey & L. Wang
CU-HTK April 2002 Switchboard System.
RT-02 workshop, May 2002 (Fairfax, VA)


This work was supported by DARPA grant MDA972-02-1-0013. The papers do not necessarily reflect the position or the policy of the US Government and no official endorsement should be inferred.

This Page is maintained by Sue Tranter,   sej28@eng.cam.ac.uk
Tues 19th April 2005