Transfer Learning Based Free-Form Speech Command Classification for Low-Resource Languages

Yohan Karunanayake, Uthayasanker Thayasivam, Surangika Ranathunga


Abstract
Current state-of-the-art speech-based user interfaces use data intense methodologies to recognize free-form speech commands. However, this is not viable for low-resource languages, which lack speech data. This restricts the usability of such interfaces to a limited number of languages. In this paper, we propose a methodology to develop a robust domain-specific speech command classification system for low-resource languages using speech data of a high-resource language. In this transfer learning-based approach, we used a Convolution Neural Network (CNN) to identify a fixed set of intents using an ASR-based character probability map. We were able to achieve significant results for Sinhala and Tamil datasets using an English based ASR, which attests the robustness of the proposed approach.
Anthology ID:
P19-2040
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
288–294
Language:
URL:
https://aclanthology.org/P19-2040
DOI:
10.18653/v1/P19-2040
Bibkey:
Cite (ACL):
Yohan Karunanayake, Uthayasanker Thayasivam, and Surangika Ranathunga. 2019. Transfer Learning Based Free-Form Speech Command Classification for Low-Resource Languages. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 288–294, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Transfer Learning Based Free-Form Speech Command Classification for Low-Resource Languages (Karunanayake et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/P19-2040.pdf