Helping Agents Help Their Users Despite Imperfect Speech Recognition
نویسندگان
چکیده
Spoken language is an important and natural way for people to communicate with computers. Nonetheless, habitable, reliable, and efficient human-machine dialogue remains difficult to achieve. This paper describes a multi-threaded semisynchronous architecture for spoken dialogue systems. The focus here is on its utterance interpretation module. Unlike most architectures for spoken dialogue systems, this new one is designed to be robust to noisy speech recognition through earlier reliance on context, a mixture of rationales for interpretation, and fine-grained use of confidence measures. We report here on a pilot study that demonstrates its robust understanding of users’ objectives, and we compare it with our earlier spoken dialogue system implemented in a traditional pipeline architecture. Substantial improvements appear at all tested levels of recognizer performance.
منابع مشابه
Reliable spelling despite poor spoken letter recognition
Speech is a powerful, flexible, and familiar interaction modality -after all, conversation is the medium of choice in human relations. Although speech recognizers promise to bring this rich, expressive channel to human-computer interaction, spoken language systems will never succeed commercially unless they compensate for imperfect recognition. Given the choice between a difficult-to-learn inte...
متن کاملWiki-like Editing of Imperfect Computer-Generated Webcast Transcripts
As the use of Internet broadcasting (webcasting) increases, more webcasts will be archived and accessed numerous times retrospectively. One challenge in skimming and browsing through such archives is the lack of textual transcripts of the archived medias’ audio channel. Ideally, transcripts would be obtainable through Automatic Speech Recognition (ASR). However, current ASR systems can only del...
متن کاملIn-home detection of distress calls: the case of aged users
In the context of technologies development aiming at helping aged people to live independently at home, the CIRDO project aims at implementing an ASR system into a social inclusion product designed for elderly people in order to detect distress situations and provide capability to call for help. In this context we present a system able to detect distress and call for help sentences on line.
متن کاملMining Free-form Spoken Responses to Tutor Prompts
How can an automated tutor assess children’s spoken responses despite imperfect speech recognition? We address this challenge in the context of tutoring children in explicit strategies for reading comprehension. We report initial progress on collecting, annotating, and mining their spoken responses. Collection and annotation yield authentic but sparse data, which we use to synthesize additional...
متن کاملIntroducing Utterance Verification in Spoken Dialogue System to Improve Dynamic Help Generation for Novice Users
A method is presented that helps novice users understand the language expressions that a system can accept, even from unacceptable utterances made that may contain automatic speech recognition errors. We have developed a method that dynamically generates help messages, which can avoid further unacceptable utterances from being made, by estimating a users’ knowledge from their utterances. To imp...
متن کامل