NWU Institutional Repository

Spoken language identification system adaptation in under-resourced environments

Loading...
Thumbnail Image

Date

Authors

Kleynhans, Neil
Barnard, Etienne

Journal Title

Journal ISSN

Volume Title

Publisher

Pattern recognition association of South Africa (PRASA)

Abstract

Speech technologies have matured over the past few decades and have made significant impacts in a variety of fields, from assistive technologies to personal assistants. However, speech system development is a resource intensive activity and requires language resources such as text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of Automatic Speech Recognition (ASR) systems in the developing world is severely inhibited. Given that few task-specific corpora exist and speech technology systems perform poorly when deployed in a new environment, we investigate the use of acoustic model adaptation. We propose a new blind deconvolution technique which rapidly adapts acoustic models to a new environment and increases their overall robustness. This new technique is utilized in a Spoken Language Identification (SLID) system and significantly improves the system’s accuracy by 6% relative to the baseline system and achieves comparable performances when compared to relatively more computationally intensive standard adaptation techniques.

Description

Keywords

Citation

Kleynhans, N. & Barnard, E. 2013. Spoken language identification system adaptation in under-resourced environments. In: Conference Proceedings of the 24th Annual Symposium of the Pattern Recognition Association of South Africa, (PRASA) Pretoria. p45-51. [http://www.prasa.org/]

Endorsement

Review

Supplemented By

Referenced By