Ho, Thi Nga and Can, Duy Cat and Chng, Eng Siong (2018) An Investigation of Word Embeddings with Deep Bidirectional LSTM for Sentence Unit Detection in Automatic Speech Transcription. In: International Conference on Asian Language Processing (IALP 2018), 15-18 November, 2018, Bandung, Indonesia. (In Press)
![[img]](https://eprints.uet.vnu.edu.vn/eprints/style/images/fileicons/application_pdf.png) |
PDF
- Published Version
Restricted to Registered users only Download (324kB) | Request a copy |
Abstract
This work investigates the effectiveness of using the word based and sub-word based embedding representations as input for a deep bidirectional Long Short-Term Memory Network for Sentence Unit Detection in Automatic Speech Recognition transcription. Our experimental results show that using sub-word based embedding can significantly improve the SUD performance when a limited text is used to train both the word embedding and the SUD model. The SUD model using the sub-word based embedding gains up to 2.07% absolute improvement in F1-score as compared to the best model trained with the word-based embedding. When tested on a domain-mismatch condition, the SUD model with sub-word based embedding trained from the in-domain data gives an approximate 2% and 1% improvement over the best model using out-of-domain embedding with reference and ASR transcription with 29.5% Word Error Rate respectively.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Information Technology (IT) |
| Divisions: | Faculty of Information Technology (FIT) |
| Depositing User: | Duy-Cat Can |
| Date Deposited: | 12 Dec 2018 06:35 |
| Last Modified: | 12 Dec 2018 06:35 |
| URI: | http://eprints.uet.vnu.edu.vn/eprints/id/eprint/3170 |
Actions (login required)
 |
View Item |
