Preserving Phonemic Distinctions For Ordinal Regression: A Novel Loss Function For Automatic Pronunciation Assessment

Bi Cheng Yan*, Hsin Wei Wang, Yi Cheng Wang, Jiun Ting Li, Chi Han Lin, Berlin Chen

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

Automatic pronunciation assessment (APA) manages to quantify the pronunciation proficiency of a second language (L2) learner in a language. Prevailing approaches to APA normally leverage neural models trained with a regression loss function, such as the mean-squared error (MSE) loss, for proficiency level prediction. Despite most regression models can effectively capture the ordinality of proficiency levels in the feature space, they are confronted with a primary obstacle that different phoneme categories with the same proficiency level are inevitably forced to be close to each other, retaining less phoneme-discriminative information. On account of this, we devise a phonemic contrast ordinal (PCO) loss for training regression-based APA models, which aims to preserve better phonemic distinctions between phoneme categories meanwhile considering ordinal relationships of the regression target output. Specifically, we introduce a phoneme-distinct regularizer into the MSE loss, which encourages feature representations of different phoneme categories to be far apart while simultaneously pulling closer the representations belonging to the same phoneme category by means of weighted distances. An extensive set of experiments carried out on the speechocean 762 benchmark dataset demonstrate the feasibility and effectiveness of our model in relation to some existing state-of-the-art models.

原文英語
主出版物標題2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9798350306897
DOIs
出版狀態已發佈 - 2023
事件2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 - Taipei, 臺灣
持續時間: 2023 12月 162023 12月 20

出版系列

名字2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

會議

會議2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
國家/地區臺灣
城市Taipei
期間2023/12/162023/12/20

ASJC Scopus subject areas

  • 人工智慧
  • 電腦視覺和模式識別
  • 訊號處理
  • 聲學與超音波
  • 語言和語言學
  • 通訊

指紋

深入研究「Preserving Phonemic Distinctions For Ordinal Regression: A Novel Loss Function For Automatic Pronunciation Assessment」主題。共同形成了獨特的指紋。

引用此