Robust recognition of Mandarin vowels by articulatory manners

Jin Hu, Jing Liu, Yingnan Zhang, Zhuanling Zha, Xiang Xie, Shilei Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a robust classifier for Mandarin vowels considering articulatory manners (AMs) which include the height of the body of the tongue, the front-back position of the tongue, and the degree of lip rounding. Firstly, the articulatory manners of each vowel are encoded to a 3-dimension vector pattern. Then, acoustic features are extracted and mapped to the articulatory manner vector by ELM. Finally, the nearest vowel to the articulatory manner vector is chosen as the recognized result. Comparison between our method and the direct method without considering the articulatory manners shows that the proposed method has an improvement of 7.1 percentage points. Tests with three kinds of noisy data in the Aurora-4 show it also outperforms the normal method with an about a gain of about 4 percentage points.

Original languageEnglish
Title of host publicationProceedings of 2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017
PublisherAssociation for Computing Machinery
Pages172-175
Number of pages4
ISBN (Electronic)9781450348287
DOIs
Publication statusPublished - 13 Jan 2017
Event2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017 - Ho Chi Minh City, Viet Nam
Duration: 13 Jan 201716 Jan 2017

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017
Country/TerritoryViet Nam
CityHo Chi Minh City
Period13/01/1716/01/17

Keywords

  • Articulatory manners
  • ELM
  • Mandarin vowel recognition
  • Robustness

Fingerprint

Dive into the research topics of 'Robust recognition of Mandarin vowels by articulatory manners'. Together they form a unique fingerprint.

Cite this

Hu, J., Liu, J., Zhang, Y., Zha, Z., Xie, X., & Huang, S. (2017). Robust recognition of Mandarin vowels by articulatory manners. In Proceedings of 2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017 (pp. 172-175). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3036290.3036314