Sub-sentence discourse models for conversational speech recognition
نویسندگان
چکیده
According to discourse theories in linguistics, conversational utterances possess an informational structure that partitions each sentence into two portions: a “given” and “new”. In this work, we explore this idea by building sub-sentence discourse language models for conversational speech recognition. The internal sentence structure is captured in statistical language modeling by training multiple n-gram models using the Expectation-Maximization algorithm on the Switchboard corpus. The resulting model contributes to a 30% reduction in language model perplexity and a small gain in word error rate.
منابع مشابه
Published in "Proceedings of ICSLP-96" Dialogue Processing in a Conversational Speech Translation System
Attempts at discourse processing of spontaneously spoken dialogue face several difficulties: multiple hypotheses that result from the parser’s attempts to make sense of the output from the speech recognizer, ambiguity that results from segmentation of multi-sentence utterances, and cumulative error — errors in the discourse context which cause further errors when subsequent sentences are proces...
متن کاملIn Proceedings of ISSD/ICSLP-96 Dialogue Processing in a Conversational Speech Translation System
Attempts at discourse processing of spontaneously spoken dialogue face several difficulties: multiple hypotheses that result from the parser’s attempts to make sense of the output from the speech recognizer, ambiguity that results from segmentation of multi-sentence utterances, and cumulative error — errors in the discourse context which cause further errors when subsequent sentences are proces...
متن کاملModeling Conversational Speech for Speech Recognition
In language modeling for speech recognition the goal is to constrain the search of the speech recognizer by providing a model which can, given a context, indicate what the next most likely word will be. In this paper, we explore how the addition of information to the text, in particular part of speech and dysfluency annotations, can be used to,build more complex language models. In particular, ...
متن کاملTowards a unified framework for sub-lexical and supra-lexical linguistic modeling
Conversational interfaces have received much attention as a promising natural communication channel between humans and computers. A typical conversational interface consists of three major systems: speech understanding, dialog management and spoken language generation. In such a conversational interface, speech recognition as the front-end of speech understanding remains to be one of the fundam...
متن کاملTowards a Unified Framework
Conversational interfaces have received much attention as a promising natural communication channel between humans and computers. A typical conversational interface consists of three major systems: speech understanding, dialog management and spoken language generation. In such a conversational interface, speech recognition as the front-end of speech understanding remains to be one of the fundam...
متن کامل