Multiband subspace tracking speech enhancement for in-car human computer speech interaction

Chung Hsien Yang, Jia Ching Wang, Jhing Fa Wang, Hsiao Ping Lee, Chung Hsien Wu, Kai Hsing Chang

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In this paper, a new subspace-based speech enhancement algorithm for in-car human computer speech interaction is presented. We first incorporate a perceptual filter-bank which is derived from psycho-acoustic model with signal subspace approach to effectively suppress in-car noises of engine. Second, for real-time applications, a new subspace tracking algorithm is derived by modifying PASTd algorithm to solve the data dependent hazard of tacking algorithm. Six different types of in-car noises in TAICAR database are used in our evaluation. The experimental results demonstrate that our approach is superior to conventional subspace and spectral subtraction methods.

Original languageEnglish
Pages (from-to)1093-1107
Number of pages15
JournalJournal of Information Science and Engineering
Volume22
Issue number5
StatePublished - 1 Sep 2006

Keywords

  • Human computer interaction
  • In-car noise
  • PASTd algorithm
  • Perceptual filterbank
  • Speech enhancement
  • Subspace tracking

Fingerprint

Dive into the research topics of 'Multiband subspace tracking speech enhancement for in-car human computer speech interaction'. Together they form a unique fingerprint.

Cite this