relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3170/
title: An Investigation of Word Embeddings with Deep Bidirectional LSTM for Sentence Unit Detection in Automatic Speech Transcription
creator: Ho, Thi Nga
creator: Can, Duy Cat
creator: Chng, Eng Siong
subject: Information Technology (IT)
description: 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.
date: 2018-11
type: Conference or Workshop Item
type: PeerReviewed
format: application/pdf
language: en
identifier: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3170/1/paper92.pdf
identifier:   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)