Ing. Lukáš Burget, Ph.D.
| Hain, T., Burget, L., Dines, J., Garner, P., N., El, H., A., Huijbregts, M., Karafiát, M., Lincoln, M., Wan, V.: The AMIDA 2009 Meeting Transcription System, In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010), Makuhari, Chiba, JP, ISCA, 2010, p. 358-361, ISBN 978-1-61782-123-3, ISSN 1990-9772 | | Publication language: | english |
|---|
| Original title: | The AMIDA 2009 Meeting Transcription System |
|---|
| Title (cs): | AMIDA 2009 systém pro rozpoznávání meetingů |
|---|
| Pages: | 358-361 |
|---|
| Proceedings: | Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010) |
|---|
| Conference: | Interspeech 2010 |
|---|
| Place: | Makuhari, Chiba, JP |
|---|
| Year: | 2010 |
|---|
| ISBN: | 978-1-61782-123-3 |
|---|
| Journal: | Proceedings of Interspeech, Vol. 2010, No. 9, FR |
|---|
| ISSN: | 1990-9772 |
|---|
| Publisher: | International Speech Communication Association |
|---|
| URL: | http://www.fit.vutbr.cz/research/groups/speech/publi/2010/burget_interspeech2010_IS100781.pdf [PDF] |
|---|
| Keywords |
|---|
| speech recognition, meeting transcription |
| Annotation |
|---|
| The paper is on systems for close-taking, far field and speaker attributed STT conditions. The system was used at participation in the NIST RT'2009 STT evaluations. |
| Abstract |
|---|
| We present the AMIDA 2009 system for participation in the NIST RT'2009 STT evaluations. Systems for close-talking, far field and speaker attributed STT conditions are described. Improvements to our previous systems are: segmentation and diarisation; stacked bottle-neck posterior feature extraction; fMPE training of acoustic models; adaptation on complete meetings; improvements to WFST decoding; automatic optimisation of decoders and system graphs. Overall these changes gave a 6-13% relative reduction in word error rate while at the same time reducing the real-time factor by a factor of five and using considerably less data for acoustic model training. |
| BibTeX: |
|---|
@INPROCEEDINGS{
author = {Thomas Hain and Lukáš Burget and John Dines and N. Phillip
Garner and Asmaa Hannani El and Marijn Huijbregts and Martin
Karafiát and Mike Lincoln and Vincent Wan},
title = {The AMIDA 2009 Meeting Transcription System},
pages = {358--361},
booktitle = {Proceedings of the 11th Annual Conference of the
International Speech Communication Association (INTERSPEECH
2010)},
journal = {Proceedings of Interspeech},
volume = {2010},
number = {9},
year = {2010},
location = {Makuhari, Chiba, JP},
publisher = {International Speech Communication Association},
ISBN = {978-1-61782-123-3},
ISSN = {1990-9772},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9365}
} |
|