Paper Info
Title
Further progress in meeting recognition: the ICSI-SRI spring 2005 speech-to-text evaluation system
Abstract
We describe the development of our speech recognition system for the National Institute of Standards and Technology (NIST) Spring 2005 Meeting Rich Transcription (RT-05S) evaluation, highlighting improvements made since last year [1]. The system is based on the SRI-ICSI-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 narrow-band (telephone) acoustic models 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 both MDM and IHM conditions compared to last year's evaluation system. Results on lecture data are comparable to the best reported results for that task.
Year
DOI
Venue
2005
10.1007/11677482_39
MLMI
Keywords
Field
DocType
last year,speech-to-text evaluation system,web data,icsi-sri spring,meeting recognition,lecture data,acoustic model,rt-04s conference data,training data,evaluation system,recognition system,added training data,rt-05s meeting data,speech to text,multilayer perceptron,speech recognition,decision tree,modeling language
Broadcasting,Computer science,Word error rate,Speech recognition,Phone,NIST,Preprocessor,Artificial intelligence,Language model,Machine learning,Microphone,Acoustic model
Conference
Volume
ISSN
ISBN
3869
0302-9743
3-540-32549-2
Citations 
PageRank 
References 
33
3.76
11
Authors
10
Name
Order
Citations
PageRank
Andreas Stolcke16690712.46
Xavier Anguera262454.28
Kofi Boakye315513.64
Özgür Çetin415414.41
Frantisek Grézl538938.12
Adam Janin625034.11
Arindam Mandal715816.44
Barbara Peskin817618.45
Chuck Wooters940458.49
Jing Zheng1044243.00