Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms

Tien Hong Lo, Yao Ting Sung, Berlin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Recently, end-to-end (E2E) models, which allow to take spectral vector sequences of L2 (second-language) learners' utterances as input and produce the corresponding phone-level sequences as output, have attracted much research attention in developing mispronunciation detection (MD) systems. However, due to the lack of sufficient labeled speech data of L2 speakers for model estimation, E2E MD models are prone to overfitting in relation to conventional ones that are built on DNN-HMM acoustic models. To alleviate this critical issue, we in this paper propose two modeling strategies to enhance the discrimination capability of E2E MD models, each of which can implicitly leverage the phonetic and phonological traits encoded in a pretrained acoustic model and contained within reference transcripts of the training data, respectively. The first one is input augmentation, which aims to distill knowledge about phonetic discrimination from a DNN-HMM acoustic model. The second one is label augmentation, which manages to capture more phonological patterns from the transcripts of training data. A series of empirical experiments conducted on the L2-ARCTIC English dataset seem to confirm the efficacy of our E2E MD model when compared to some top-of-the-line E2E MD models and a classic pronunciation-scoring based method built on a DNN-HMM acoustic model.

Original languageEnglish
Title of host publication2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1049-1055
Number of pages7
ISBN (Electronic)9789881476890
Publication statusPublished - 2021
Event2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Tokyo, Japan
Duration: 2021 Dec 142021 Dec 17

Publication series

Name2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings

Conference

Conference2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021
Country/TerritoryJapan
CityTokyo
Period2021/12/142021/12/17

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Instrumentation

Fingerprint

Dive into the research topics of 'Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms'. Together they form a unique fingerprint.

Cite this