Publication Details

Investigation into bottle-neck features for meeting speech recognition

GRÉZL František, KARAFIÁT Martin and BURGET Lukáš. Investigation into bottle-neck features for meeting speech recognition. In: Proc. Interspeech 2009. Brighton: International Speech Communication Association, 2009, pp. 2947-2950. ISBN 978-1-61567-692-7. ISSN 1990-9772.
Czech title
Výzkum bottle-neck parametrů v rozpoznávání řeči z meetingů
Type
conference paper
Language
english
Authors
URL
Keywords

Bottle-neck, ANN architecture, features, LVCSR

Abstract

The paper is on investigation into bottle-neck features for meeting speech recognition. The bottle-neck ANN structure is imported into Split Context architecture gaining significant WER reduction.

Annotation

This work investigates into recently proposed Bottle-Neck features for ASR. The bottle-neck ANN structure is imported into Split Context architecture gaining significant WER reduction. Further, Universal Context architecture was developed which simplifies the system by using only one universal ANN for all temporal splits. Significant WER reduction can be obtained by applying fMPE on top of our BN features as a technique for discriminative feature extraction and further gain is also obtained by retraining model parameters using MPE criterion. The results are reported on meeting data from RT07 evaluation

Published
2009
Pages
2947-2950
Journal
Proceedings of Interspeech - on-line, no. 9, ISSN 1990-9772
Proceedings
Proc. Interspeech 2009
Conference
Interspeech Conference, Brighton, GB
ISBN
978-1-61567-692-7
Publisher
International Speech Communication Association
Place
Brighton, GB
BibTeX
@INPROCEEDINGS{FITPUB9038,
   author = "Franti\v{s}ek Gr\'{e}zl and Martin Karafi\'{a}t and Luk\'{a}\v{s} Burget",
   title = "Investigation into bottle-neck features for meeting speech recognition",
   pages = "2947--2950",
   booktitle = "Proc. Interspeech 2009",
   journal = "Proceedings of Interspeech - on-line",
   number = 9,
   year = 2009,
   location = "Brighton, GB",
   publisher = "International Speech Communication Association",
   ISBN = "978-1-61567-692-7",
   ISSN = "1990-9772",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9038"
}
Back to top