Attention, intentions, and the structure of discourse
Computational Linguistics
Pitch accent in context: predicting intonational prominence from text
Artificial Intelligence - Special volume on natural language processing
Centering: a framework for modeling the local coherence of discourse
Computational Linguistics
The computational processing of intonational prominence: a functional prosody perspective
The computational processing of intonational prominence: a functional prosody perspective
Multilingual Text-to-Speech Synthesis
Multilingual Text-to-Speech Synthesis
Evaluating automated and manual acquisition of anaphora resolution strategies
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
A new statistical parser based on bigram lexical dependencies
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
A prosodic analysis of discourse segments in direction-giving monologues
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Cue phrase classification using machine learning
Journal of Artificial Intelligence Research
Modeling local context for pitch accent prediction
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Using dialogue representations for concept-to-speech generation
ANLP/NAACL-ConvSyst '00 Proceedings of the 2000 ANLP/NAACL Workshop on Conversational systems - Volume 3
Using dialogue representations for concept-to-speech generation
ConversationalSys '00 Proceedings of the ANLP-NAACL 2000 Workshop on Conversational Systems
Hi-index | 0.00 |
Near-perfect automatic accent assignment is attainable for citation-style speech, but better computational models are needed to predict accent in extended, spontaneous discourses. This paper presents an empirically motivated theory of the discourse focusing nature of accent in spontaneous speech. Hypotheses based on this theory lead to a new approach to accent prediction, in which patterns of deviation from citation form accentuation, defined at the constituent or noun phrase level, are automatically learned from an annotated corpus. Machine learning experiments on 1031 noun phrases from eighteen spontaneous direction-giving monologues show that accent assignment can be significantly improved by up to 4%-6% relative to a hypothetical baseline system that would produce only citation-form accentuation, giving error rate reductions of 11%-25%.