Speech Recognition Based on Fusion of Visual and Auditory Information Using Full-Frame Color Image

• IGAWA Satoru

  College of Engineering, Osaka Prefecture University

• OGIHARA Akio

  College of Engineering, Osaka Prefecture University

• SHINTANI Akira

  College of Engineering, Osaka Prefecture University

• TAKAMATSU Shinobu

  College of Engineering, Osaka Prefecture University

抄録

We propose a method to fuse auditory information and visual information for accurate speech recognition. This method fuses two kinds of information by using linear combination after calculating two kinds of probabilities by HMM for each word. In addition, we use full-frame color image as visual information in order to improve the accuracy of the proposed speech recognition system. We have performed experiments comparing the proposed method with the method using either auditory in-formation or visual information, and confirmed the validity of the proposed method.

収録刊行物

• IEICE transactions on fundamentals of electronics, communications and computer sciences

  IEICE transactions on fundamentals of electronics, communications and computer sciences 79 (11), 1836-1840, 1996-11-25

  一般社団法人電子情報通信学会

キーワード

• speech recognition
• fusion of visual and auditory
• sensor fusion
• hidden Markov model

詳細情報

• CRID: 1570009752557976192
• NII論文ID: 110003216080
• NII書誌ID: AA10826239
• ISSN: 09168508
• 本文言語コード: en
• データソース種別:
  • CiNii Articles