Articulatory information for noise robust speech recognition

Vikramjit Mitra, Hosung Nam, Carol Y. Espy-Wilson, Elliot Saltzman, Louis Goldstein

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Prior research has shown that articulatory information, if extracted properly from the speech signal, can improve the performance of automatic speech recognition systems. However, such information is not readily available in the signal. The challenge posed by the estimation of articulatory information from speech acoustics has led to a new line of research known as "acoustic-to- articulatory inversion" or "speech-inversion." While most of the research in this area has focused on estimating articulatory information more accurately, few have explored ways to apply this information in speech recognition tasks. In this paper, we first estimated articulatory information in the form of vocal tract constriction variables (abbreviated as TVs) from the Aurora-2 speech corpus using a neural network based speech-inversion model. Word recognition tasks were then performed for both noisy and clean speech using articulatory information in conjunction with traditional acoustic features. Our results indicate that incorporating TVs can significantly improve word recognition rates when used in conjunction with traditional acoustic features.

Original languageEnglish
Article number5677601
Pages (from-to)1913-1924
Number of pages12
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume19
Issue number7
DOIs
Publication statusPublished - 2011
Externally publishedYes

Keywords

  • Articulatory phonology
  • articulatory speech recognition
  • artificial neural networks (ANNs)
  • noise-robust speech recognition
  • speech inversion
  • task dynamic model
  • vocal-tract variables

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Articulatory information for noise robust speech recognition'. Together they form a unique fingerprint.

Cite this