Přístupnostní navigace
E-application
Search Search Close
Publication detail
STOLCKE, A., ANGUERA, X., BOAKYE, K., CETIN, Ö., GRÉZL, F., JANIN, A., MANDAL, A., PESKIN, B., WOOTERS, C., ZHENG, J.
Original Title
Further Progress in Meeting Recognition: The ICSI-SRI Spring 2005 Speech-to-Text Evaluation System
Type
conference paper
Language
English
Original Abstract
We describe the development of our speech recognition system forthe NIST Spring 2005 Meeting Rich Transcription (RT-05S) evaluation, highlighting improvements made since last year. The system is based on the SRIICSI-UW RT-04F conversational telephone speech (CTS) recognition system, with meeting-adapted models and various audio preprocessing steps. This year's system features better delay-sum processing of distant microphone channels and energy-based crosstalk suppression for close-talking microphones. Acoustic modeling is improved by virtue of various enhancements to the background (CTS) models, including added training data, decision-tree based state tying, and the inclusion of discriminatively trained phone posterior features estimated by multilayer perceptrons. In particular, we make use of adaptation of both acoustic models and MLP features to the meeting domain. For distant microphone recognition we obtained considerable gains by combining and cross-adapting narrowband (telephone) acousticmodels with broadband (broadcast news) models. Language models (LMs) were improved with the inclusion of new meeting and web data. In spite of a lack of training data, we created effective LMs for the CHIL lecture domain. Results are reported on RT-04S and RT-05S meeting data. Measured on RT-04S conference data, we achieved an overall improvement of 17% relative in bothMDM and IHMconditions compared to last year's evaluation system. Results on lecture data are comparable to the best reported results for that task.
Keywords
speech-to-text system, rich transcription, system adaptation
Authors
RIV year
2005
Released
13. 7. 2005
Publisher
University of Edinburgh
Location
Edinburgh, Scotland
ISBN
978-3-540-32549-9
Book
Machine Learning for Multimodal Interaction, Second International Workshop, MLMI 2005, Edinburgh, UK, July 11-13, 2005, Revised Selected Papers
Edition
Lecture Notes in Computer Science 3869, Springer 2006
Pages from
463
Pages to
475
Pages count
12
BibTex
@inproceedings{BUT18258, author="Andreas {Stolcke} and Xavier {Anguera} and Kofi {Boakye} and Özgür {Cetin} and František {Grézl} and Adam {Janin} and Arindam {Mandal} and Barbara {Peskin} and Chuck {Wooters} and Jing {Zheng}", title="Further Progress in Meeting Recognition: The ICSI-SRI Spring 2005 Speech-to-Text Evaluation System", booktitle="Machine Learning for Multimodal Interaction, Second International Workshop, MLMI 2005, Edinburgh, UK, July 11-13, 2005, Revised Selected Papers", year="2005", series="Lecture Notes in Computer Science 3869, Springer 2006", pages="463--475", publisher="University of Edinburgh", address="Edinburgh, Scotland", isbn="978-3-540-32549-9" }