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

The system described is an extension of TOSBURG (taste-oriented speech dialogue system based on speech understanding and response generation), TOSBURG II. To facilitate robust human-computer interaction, a new component has been introduced: adaptive cancellation of synthetic speech response. In addition, noise immunity learning has been extended to dialogue speech contaminated by an 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. A user-initiated dialogue manager and a multimodal response generator have been integrated to construct a speaker-independent dialogue system for a fast-food ordering task. Experimental results have shown the effectiveness of adaptive speech response cancellation and the extension of noise immunity learning.<>