Mispronunciation detection leveraging maximum performance criterion training of acoustic models and decision functions

Yao Chi Hsu, Ming Han Yang, Hsiao Tsung Hung, Berlin Chen

Research output: Contribution to journalConference article

5 Citations (Scopus)


Mispronunciation detection is part and parcel of a computer assisted pronunciation training (CAPT) system, facilitating second-language (L2) learners to pinpoint erroneous pronunciations in a given utterance so as to improve their spoken proficiency. This paper presents a continuation of such a general line of research and the major contributions are twofold. First, we present an effective training approach that estimates the deep neural network based acoustic models involved in the mispronunciation detection process by optimizing an objective directly linked to the ultimate evaluation metric. Second, along the same vein, two disparate logistic sigmoid based decision functions with either phone- or senone-dependent parameterization are also inferred and used for enhanced mispronunciation detection. A series of experiments on a Mandarin mispronunciation detection task seem to show the performance merits of the proposed method.

Original languageEnglish
Pages (from-to)2646-2650
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2016 Jan 1
Event17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 - San Francisco, United States
Duration: 2016 Sep 82016 Sep 16



  • Computer assisted pronunciation training
  • Deep neural networks
  • Discriminative training
  • Mispronunciation detection

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this