Juan, Sarah Samson and Besacier, Laurent and Lecouteux, Benjamin and Dyab, Mohamed (2015) Using Resources from a Closely-related Language to Develop ASR for a Very Under-resourced Language: A Case Study for Iban. In: Proceedings of INTERSPEECH 2015, September 2015, Dresden, Germany.
|
PDF
IS2015_samsonjuan_camera-ready.pdf Download (127kB) | Preview |
Abstract
This paper presents our strategies for developing an automatic speech recognition system for Iban, an under-resourced language. We faced several challenges such as no pronunciation dictionary and lack of training material for building acoustic models. To overcome these problems, we proposed approaches which exploit resources from a closely-related language (Malay). We developed a semi-supervised method for building the pronunciation dictionary and applied cross-lingual strategies for improving acoustic models trained with very limited training data. Both approaches displayed very encouraging results, which show that data from a closely-related language, if available, can be exploited to build ASR for a new language. In the final part of the paper, we present a zero-shot ASR using Malay resources that can be used as an alternative method for transcribing Iban speech.
| Item Type: | Proceeding (Paper) |
|---|---|
| Uncontrolled Keywords: | speech recognition, low resource languages, cross-lingual training, zero-shot ASR, Universiti Malaysia Sarawak, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology Faculties, Institutes, Centres > Faculty of Computer Science and Information Technology Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology |
| Depositing User: | Samson Juan |
| Date Deposited: | 16 Oct 2015 01:23 |
| Last Modified: | 16 Oct 2015 01:23 |
| URI: | http://ir.unimas.my/id/eprint/8883 |
Actions (For repository members only: login required)
 |
View Item |
