Noisy spontaneous speech understanding using noise immunity keyword spotting with adaptive speech response cancellation

  • Authors:
  • Yoichi Takebayashi;Yoshifumi Nagata;Hiroshi Kanazawa

  • Affiliations:
  • Toshiba Corporation, Research & Development Center, Kawasaki, Japan;Toshiba Corporation, Research & Development Center, Kawasaki, Japan;Toshiba Corporation, Research & Development Center, Kawasaki, Japan

  • Venue:
  • ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

We have developed a noisy spontaneous speech understanding system using Noise Immunity keyword spotting with adaptive speech response cancellation. We have employed a keyword-based approach to understand spontaneous speech. To facilitate robust human-computer interaction, we have introduced a new component to the system: adaptive cancellation of synthetic speech response. We have also extended Noise Immunity Learning to dialogue speech contaminated by a uncancelled component of a synthetic speech response. The cancellation allows the user to interrupt speech responses of the system for more efficient human-computer interaction. We have integrated a user-initiated dialogue manager and a multimodal response generator to construct a speaker-independent dialogue system for a fast-food ordering task. The experimental results have shown the effectiveness of adaptive speech response cancellation and the extension of Noise Immunity Learning.