Robust Recognition of Speech with Background Music in Acoustically Under-Resourced Scenarios

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F18%3A00006123" target="_blank" >RIV/46747885:24220/18:00006123 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/ICASSP.2018.8462674" target="_blank" >http://dx.doi.org/10.1109/ICASSP.2018.8462674</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2018.8462674" target="_blank" >10.1109/ICASSP.2018.8462674</a>

Result language
angličtina
Original language name
Robust Recognition of Speech with Background Music in Acoustically Under-Resourced Scenarios
Original language description
This paper addresses the task of Automatic Speech Recognition (ASR) with music in the background. We consider two different situations: 1) scenarios with very small amount of labeled training utterances (duration 1 hour) and 2) scenarios with large amount of labeled training utterances (duration 132 hours). In these situations, we aim to achieve robust recognition. To this end we investigate the following techniques: a) multi-condition training of the acoustic model, b) denoising autoencoders for feature enhancement and c) joint training of both above mentioned techniques. We demonstrate that the considered methods can be successfully trained with the small amount of labeled acoustic data. We present substantially improved performance compared to acoustic models trained on clean speech. Further, we show a significant increase of accuracy in the under-resourced scenario, when utilizing additional amount of non-labeled data. Here, the non-labeled dataset is used to improve the accuracy of the feature enhancement via autoencoders. Subsequently, the autoencoders are jointly fine-tuned along with the acoustic model using the small amount of labeled utterances.
Czech name
—
Czech description
—

Project
<a href="/en/project/TH03010018" target="_blank" >TH03010018: DeepSpot - Multilingual technology for spotting and instant alerting</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISBN
978-153864658-8
ISSN
1520-6149
e-ISSN
—
Number of pages
5
Pages from-to
5624-5628
Publisher name
IEEE
Place of publication
Kanada
Event location
Calgary, Kanada
Event date
Jan 1, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000446384605157

Similar results(10)