Yasuhisa Niimi

Learn More
This paper describes a system to synthesize emotional speech based on TDPLOSA. The system has a database of VCV (vowel consonant vowel) segments for each of three emotions; anger, sadness and joy. These segments have emotional speech quality. The database contains four kinds of VCV segments which are prosodically balanced in the sense that their(More)
This paper considers a dialog control strategy based on the reliability of speech recognition. The spoken dialog system using this strategy accepts an utterance of the user if the reliability is high, while it rejects the utterance and asks the user to speak again (the basic strategy), or con rms the content of the utterance if the reliability is low. The(More)
Voice-mail and video-mail systems for the Internet are becoming very popular, because the speech and video compression technology is greatly improved in these days. Asynchronous voice-mail system, however, does not seem attractive because it's not designed for discussions. We propose a network-based voice conference system which enables asynchronous and(More)
This paper presents a task-independent dialogue control scheme, which is an extension of the frame-driven method. A spoken dialogue system, SDSKIT-3, which is based on this scheme, has been developed for the tourist information service and has demonstrated it can manage problems which are encountered in a spoken dialogue system. The scheme is transported to(More)
This paper proposes and analyzes mathematically an interactive strategy to recover from misrecognition of utterances including multiple information items through a short conversation with a speaker. First the speech recognizer in a dialogue system recognizes an utterance and evaluates the reliability of each item contained in it. The dialogue system accepts(More)
We propose a semi-automatic dialogue system generator from the Internet information contents. We classify the practical Web site into three classes of task: slot-filling, database search, and explanation. Using three levels of dialogue library for each task, our generator translates XML based Web site into VoiceXML, which controls a conversation between a(More)
It is important for visually impaired persons to have the opportunity to take lessons specialized for the visually impaired and novice PC users. From this viewpoint, we designed and implemented the UKK system, which guides the typing lessons with recorded sound and synthesized speech. We also investigated the usability of the popular e-mail tools that the(More)