Using the Tilt Intonation Model: A Data-Driven Approach

Black, Alan W.; Dusterhoff, Kurt E; Taylor, Paul

doi:10.1007/978-1-4757-3413-3_9

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous experiments which have used this techniques ([5] [2]) have also benefitted from minor handoptimising of the feature set for noise reduction. However, it is unclear whether the resulting, nominal improvement in correlation (2 percentage points) over a large corpus has any real effect.…”

Section: Building Regression Treesmentioning

confidence: 99%

Secondary codebook storage quantisation

Dusterhoff¹,

Black²,

Taylor³

1999

6th European Conference on Speech Communication and Technology

Self Cite

View full text Add to dashboard Cite

This paper presents an intonation generation system for use in a text-to-speech synthesis system. The intonation generation system uses classification trees to predict intonation event location and regression trees to predict parameters relating to the F0 shape for the predicted events. The decision trees model intonation within the Tilt intonation model, which provides a parameterized description of fundmaental frequency and an intuitive labelling scheme. The event location trees predict an event class (e.g. accent, boundary, none) for each syllable in an utterance based on local and global context (e.g. stress, phrasing, part of speech). The parameter prediction trees then provide the parameterized description of each intonation event based on similar context features. Informal results of the full system are presented together with results for the individual components.

show abstract

Section: Building Regression Treesmentioning

confidence: 99%