Paper published in a book (Scientific congresses, symposiums and conference proceedings)
An Evaluation of Unsupervised Acoustic Model Training for a Dysarthric Speech Interface
Walter, Oliver; DESPOTOVIC, Vladimir; Haeb-Umbach, Reinhold et al.
2014In Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)
Peer reviewed
 

Files


Full Text
INTERSPEECH 2014.pdf
Publisher postprint (143.26 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
unsupervised learning; acoustic unit descriptors; dysarthric speech; non-negative matrix factorization
Abstract :
[en] In this paper, we investigate unsupervised acoustic model training approaches for dysarthric-speech recognition. These models are first, frame-based Gaussian posteriorgrams, obtained from Vector Quantization (VQ), second, so-called Acoustic Unit Descriptors (AUDs), which are hidden Markov models of phone-like units, that are trained in an unsupervised fashion, and, third, posteriorgrams computed on the AUDs. Experiments were carried out on a database collected from a home automation task and containing nine speakers, of which seven are considered to utter dysarthric speech. All unsupervised modeling approaches delivered significantly better recognition rates than a speaker-independent phoneme recognition baseline, showing the suitability of unsupervised acoustic model training for dysarthric speech. While the AUD models led to the most compact representation of an utterance for the subsequent semantic inference stage, posteriorgram-based representations resulted in higher recognition rates, with the Gaussian posteriorgram achieving the highest slot filling F-score of 97.02%.
Disciplines :
Computer science
Author, co-author :
Walter, Oliver;  University of Paderborn > Department of Communications Engineering
DESPOTOVIC, Vladimir ;  University of Paderborn > Department of Communications Engineering
Haeb-Umbach, Reinhold;  University of Paderborn > Department of Communications Engineering
Gemmeke, Jort;  Katholieke Universiteit Leuven - KUL > ESAT - PSI, Processing Speech and Images
Van hamme, Hugo;  Katholieke Universiteit Leuven - KUL > ESAT - PSI, Processing Speech and Images
Ons, Bart;  Katholieke Universiteit Leuven - KUL > ESAT - PSI, Processing Speech and Images
External co-authors :
yes
Language :
English
Title :
An Evaluation of Unsupervised Acoustic Model Training for a Dysarthric Speech Interface
Publication date :
September 2014
Event name :
15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)
Event place :
Singapore, Singapore
Event date :
from 14-09-2014 to 18-09-2014
Audience :
International
Main work title :
Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)
Pages :
1013-1017
Peer reviewed :
Peer reviewed
Funders :
DFG - Deutsche Forschungsgemeinschaft [DE]
IWT-SBO
CE - Commission Européenne [BE]
Available on ORBilu :
since 05 November 2019

Statistics


Number of views
85 (1 by Unilu)
Number of downloads
64 (0 by Unilu)

Scopus citations®
 
11
Scopus citations®
without self-citations
8

Bibliography


Similar publications



Contact ORBilu