C-TOBI-Based Pitch Accent Prediction Using Maximum-Entropy Model

Kim, Byeongchang; Lee, Gary Geunbae

doi:10.1007/11751595_3

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attempts to automate pitch accent labeling from acoustic features have tended to focus on locating, rather than classifying, pitch accents [28], [29], have classified only a very limited subset of pitch accents for adult-directed speech [30], or have classified pitch accents for languages beside English [31]. Pitch accents have been statistically clustered with high agreement (78%) with listeners' judgments, suggesting acoustic regularities distinguishing pitch accent categories [32].…”

Section: Acoustic Methodologymentioning

confidence: 99%

What prosody tells infants to believe

Kim

Gold

Scassellati

2008

2008 7th IEEE International Conference on Development and Learning

View full text Add to dashboard Cite

Abstract-We examined whether evidence for prosodic signals about shared belief can be quantitatively found within the acoustic signal of infant-directed speech. Two transcripts of infant-directed speech for infants aged 1;4 and 1;6 were labeled with distinct speaker intents to modify shared beliefs, based on Pierrehumbert and Hirschberg's theory of the meaning of prosody [1]. Acoustic predictions were made from intent labels first within a simple single-tone model that reflected only whether the speaker intended to add a word's information to the discourse (high tone, H*) or not (low tone, L*). We also predicted pitch within a more complicated five-category model that added intents to suggest a word as one of several possible alternatives (L*+H), a contrasting alternative (L+H*), or something about which the listener should make an inference (H*+L). The acoustic signal was then manually segmented and automatically classified based solely on whether the pitches at the beginning, end, and peak intensity points of stressed syllables in salient words, were closer to the utterance's pitch minimum or maximum on a log scale.

show abstract