Investigating Manifold Learning Technique for Robust Speech Recognition

Bi Cheng Yan, Chin Hong Shih, Berlin Chen, Shih Hung Liu

研究成果: 書貢獻/報告類型會議貢獻

摘要

Developing robustness methods is imperative to retaining good performance for automatic speech recognition (ASR)systems when being confronted with different environmental noise or channel distortion. Previous studies have pointed out that exploration of low-dimensional structures of speech features is beneficial to generating robust features so as to enhance ASR performance. Along this research direction, we argue that the intrinsic structures of speech features lying on a manifold subspace of low dimensionality residing in their original ambient space of high dimensionality. This way, noise components can be ruled out by projecting noisy speech features into the pre-learned subspace of manifold structures. This paper explores the intrinsic geometric low-dimensional manifold structures inherent speech features' modulation spectra, with the goal to generate speech features that are more robust to environmental noise and channel distortion. The key novelty of our work is two-fold: 1)we put forward an innovative use of the graph-regularization based method to generate robust speech features by preserving the inherent manifold structures of modulation spectra and excluding irrelevant ones, and 2)we also compare our approach with several mainstream methods that also explores low-dimensional structures of data instances with in-depth analysis. A comprehensive set of empirical experiments carried out on an ASR benchmark task seem to reveal the superior performance of our proposed methods.

原文英語
主出版物標題Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018
編輯Minghui Dong, Fariska Z. Ruskanda, Herry Sujaini, Ade Romadhony, Moch. Bijaksana, Elvira Nurfadhilah, Lyla Ruslana Aini, Arif Bijaksana Putra Negara
發行者Institute of Electrical and Electronics Engineers Inc.
頁面68-73
頁數6
ISBN(電子)9781728111766
DOIs
出版狀態已發佈 - 2019 一月 28
事件22nd International Conference on Asian Language Processing, IALP 2018 - Bandung, 印度尼西亚
持續時間: 2018 十一月 152018 十一月 17

出版系列

名字Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018

會議

會議22nd International Conference on Asian Language Processing, IALP 2018
國家印度尼西亚
城市Bandung
期間18/11/1518/11/17

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Computer Science Applications

指紋 深入研究「Investigating Manifold Learning Technique for Robust Speech Recognition」主題。共同形成了獨特的指紋。

引用此