Investigating Manifold Learning Technique for Robust Speech Recognition

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

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


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.

Original languageEnglish
Title of host publicationProceedings of the 2018 International Conference on Asian Language Processing, IALP 2018
EditorsMinghui Dong, Moch. Bijaksana, Herry Sujaini, Arif Bijaksana Putra Negara, Ade Romadhony, Fariska Z. Ruskanda, Elvira Nurfadhilah, Lyla Ruslana Aini
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781728111766
Publication statusPublished - 2018 Jul 2
Event22nd International Conference on Asian Language Processing, IALP 2018 - Bandung, Indonesia
Duration: 2018 Nov 152018 Nov 17

Publication series

NameProceedings of the 2018 International Conference on Asian Language Processing, IALP 2018


Conference22nd International Conference on Asian Language Processing, IALP 2018


  • automatic speech recognition
  • low-dimensional structures
  • manifold learning
  • robustness

ASJC Scopus subject areas

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


Dive into the research topics of 'Investigating Manifold Learning Technique for Robust Speech Recognition'. Together they form a unique fingerprint.

Cite this