Domain-independent spoken dialogue platform using key-phrase spotting based on combined language model
نویسندگان
چکیده
We present a portable platform for spoken dialogue systems and its experimental evaluation. Conventional development of speech interfaces involves much labor cost in either describing a task grammar or collecting a task corpus. Our platform automatically generates a lexicon and a language model of keyphrases based on task description and structure of the domain database. By spotting key-phrases using both the generated grammar and word 2-gram model trained with dialogue corpora of similar domains, we realize flexible speech understanding on a variety of utterances. Furthermore, adopting a GUI that explicitly displays acceptable utterance patterns is effective in guiding user utterances within the system’s capability. We evaluate the generated spoken dialogue system using 24 novice users. The number of unacceptable utterances are significantly reduced with the simple phrase grammar and GUI. And the phrase spotter using the combined language model improves the semantic accuracy by 15.5% compared with the conventional method decoding the whole sentence with a fixed grammar.
منابع مشابه
Improving on Phrase Spotting for Spoken Dialogue Processing
In a typical task oriented dialogue system, the interpretation task consists of mapping from the acoustic input to a series of moves. In the simplest cases each move is just a pairing of slots and values e.g. “destination = paris”. In this paper we will describe a system for language interpretation which is designed to work with lattice based output from a class based statistical language model...
متن کاملA syllable-based Chinese spoken dialogue system for telephone directory services primarily trained with a corpus
This paper presents a syllable-based Chinese spoken dialogue system for telephone directory services primarily trained with a corpus. It integrates automatic phrase extraction, robust phrase spotting, statistics-based semantic parsing by phrase-concept joint language model as well as concept-based dialogue model, and intention identification by probabilistic finite state network to form a speec...
متن کاملDomain-Independent Platform of Spoken Dialogue Interfaces for Information Query
A domain-independent platform of spoken dialogue systems is presented. It assumes that information query is done by a sequence of key-phrases corresponding to search keys, which can be dened by a domain database. A GUI is incorporated to display typical phrase patterns for guidance and to promptly present recognition and query results for con rmation. The platform consists of general-purpose sp...
متن کاملRobust parsing of utterances in negotiative dialogue
The rapidly increasing number of spoken-dialogue systems have led to numerous robust parsers for limited domains having been constructed during the last decade. By “parsing” we here mean a mapping from the input utterance to a context-independent semantic representation. By “robust” we mean that the parser will give a reasonable result even on very noisy input. In simple spoken-dialogue applica...
متن کاملRobust Parsing of Utterances i
The rapidly increasing number of spoken-dialogue systems have led to numerous robust parsers for limited domains having been constructed during the last decade. By “parsing” we here mean a mapping from the input utterance to a context-independent semantic representation. By “robust” we mean that the parser will give a reasonable result even on very noisy input. In simple spoken-dialogue applica...
متن کامل