Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages
Loading...
Date
2013
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Spolecnost Pro Radioelektronicke Inzenyrstvi
Technická Univerzita v Liberci
Technical university of Liberec, Czech Republic
Technická Univerzita v Liberci
Technical university of Liberec, Czech Republic
Abstract
When adapting an existing speech recognition system to a new language, major development costs are associated with the creation of an appropriate acoustic model (AM). For its training, a certain amount of recorded and annotated speech is required In this paper, we show that not only the annotation process, but also the process of speech acquisition can be automated to minimize the need of human and expert work. We demonstrate the proposed methodology on Croatian language, for which the target AM has been built via cross-lingual adaptation of a Czech AM in 2 ways: a) using the commercially available GlobalPhone database, and b) by automatic speech data mining from HRT radio archive. The latter approach is cost-free, yet it yields comparable or better results in experiments conducted on 3 Croatian test sets.
Description
Subject(s)
Speech recognition, acoustic model, cross-lingual adaptation, Slavic languages
Citation
ISSN
1210-2512