Publications
Detail of publication
Citation
p. 2458-2463, Shanghai, 2011. : Real-time Large Vocabulary Spontaneous Speech Recognition for Spoken Dialog Systems . Proceedings of the 4th International Congress on Image and Signal Processing,
Download PDF
Abstract
This paper describes the method for modifying the baseline speech recognition system to be suitable for a use in spoken dialog system with mixed initiative and natural user's input. We present three approaches for extending the recognition vocabulary to ensure the spoken dialog system is able to recognize all entities in the given domain. The colloquial text normalization method is proposed. The experiments performed on spontaneous speech corpus suggested that the proposed method is very important for languages where the formal written language and a common colloquial speech are very different. The overall word error rate was reduced by 16.7%.
Detail of publication
Title: | Real-time Large Vocabulary Spontaneous Speech Recognition for Spoken Dialog Systems |
---|---|
Author: | Jan Švec ; Luboš Šmídl |
Language: | English |
Year: | 2011 |
Type of publication: | Papers in proceedings of reviewed conferences |
Title of journal or book: | Proceedings of the 4th International Congress on Image and Signal Processing |
Page: | 2458 - 2463 |
ISBN: | 978-1-4577-1446-7 |
Address: | Shanghai |
Keywords
speech recognition, language modeling, spoken dialog system
BibTeX
@INPROCEEDINGS{JanSvec_2011_Real-timeLarge, author = {Jan \v{S}vec and Lubo\v{s} \v{S}m\'{i}dl}, title = {Real-time Large Vocabulary Spontaneous Speech Recognition for Spoken Dialog Systems}, year = {2011}, journal = {Proceedings of the 4th International Congress on Image and Signal Processing}, address = {Shanghai}, pages = {2458-2463}, ISBN = {978-1-4577-1446-7}, url = {http://www.kky.zcu.cz/en/publications/JanSvec_2011_Real-timeLarge}, }