Speech Interface Exploiting Intentionally-Controlled Nonverbal Speech Information

This paper describes our research on speech interfaces using nonverbal speech information. Although speech information consists of verbal and nonverbal information, most speechrecognition research has made use of only verbal information such as words and sentences. From among nonverbal information, we have focused on hesitation (filled pause) and prosody (voice pitch) to create four speech-interface functions: Speech Completion, Speech Shift, Speech Starter, and Speech Spotter. Hesitation, for example, can be used as a trigger to complete an uttered fragment and pitch changing can be used to enter a word with it having different functions. By having users intentionally utter nonverbal information according to simple rules, we have achieved interfaces that can exploit the potential of speech in various forms. ACM Classification: H5.2 [Information interfaces and presentation]: User Interfaces. Voice I/O. General Terms: Design, Human Factors