Modelling prominence and emphasis improves unit-selection synthesis
Autor: | Dan Jurafsky, Simon King, Ani Nenkova, Jason Brenier, Volker Strom, Robert A. J. Clark, Yolanda Vazquez-Alvarez |
---|---|
Rok vydání: | 2007 |
Předmět: |
Pitch accent
Computer science business.industry Speech recognition media_common.quotation_subject Contrast (statistics) Speech synthesis computer.software_genre Scale (music) speech synthesis Perception Selection (linguistics) Artificial intelligence Prosody business computer Natural language processing media_common |
Zdroj: | INTERSPEECH Scopus-Elsevier Strom, V, Nenkova, A, Clark, R, Vazquez-Alvarez, Y, Brenier, J, King, S & Jurafsky, D 2007, Modelling Prominence and Emphasis Improves Unit-Selection Synthesis . in Interspeech 2007 : 8th Annual Conference of the International Speech Communication Association . pp. 1282-1285 . |
DOI: | 10.21437/interspeech.2007-230 |
Popis: | We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously prominence assignment has been mainly evaluated by computing accuracy on a prominence-labelled test set. By contrast we integrated an automatic pitch-accent classifier into the unit selection target cost and showed that listeners preferred these synthesised sentences. We also describe an improved recording script for collecting emphatic accents, and show that generating emphatic accents leads to further improvements in the fiction genre over incorporating pitch accent only. Finally, we show differences in the effects of prominence between child-directed speech and news and fiction genres. Index Terms: speech synthesis, prosody, prominence, pitch accent, unit selection |
Databáze: | OpenAIRE |
Externí odkaz: |