White Papers

Audio-Visual Speech Recognition in Challenging Environments

Overview Visual speech information is known to improve accuracy and noise robustness of Automatic Speech Recognizers (ASR). However, to date, all audio-visual ASR work has concentrated on "Visually clean" data with limited variation in the speaker's frontal pose, lighting, and background. In this paper, one investigates audiovisual ASR in two practical environments that present significant challenges to robust visual processing: Typical offices, where data are recorded by means of a portable PC equipped with an inexpensive web camera, and Automobiles, with data collected at three approximate speeds. The performance of all components of a state-of-the-art audio-visual ASR system is reported on these two sets and benchmarked against "Visually clean" data recorded in a studio-like environment.

Further White Paper Details
PublisherIBM File FormatPDF
Date PublishedSeptember 2003
FormatWhite Papers   
Topics
    N/A
  • Download White Paper
  • Yes, useful No, not useful Did you find this white paper useful?