Intonation Template Matching for Syllable-Level Prosody Encoding
Authors: Rehman, A., Zhang, J.J. and Yang, X.
Journal: CEUR Workshop Proceedings
Volume: 3644
ISSN: 1613-0073
Abstract:We address the challenge of machine interpretation of subtle speech intonations that convey complex meanings. We assume that emotions and interrogative statements follow regular prosodic patterns, allowing us to create an unsupervised intonation template dictionary. These templates can then serve as encoding mechanisms for higher-level labels. We use piecewise interpolation of syllable-level formant features to create intonation templates and evaluate their effectiveness on three speech emotion recognition datasets and declarative-interrogative utterances. The results indicate that individual syllables can be detected for basic emotions with nearly double the accuracy of chance. Additionally, certain intonation templates exhibit a correlation with interrogative implications.
https://eprints.bournemouth.ac.uk/39773/
Source: Scopus
Intonation Template Matching for Syllable-Level Prosody Encoding
Authors: Rehman, A., Zhang, J.J. and Yang, X.
Editors: Villagrá, P.L. and Li, X.
Volume: 3644
Publisher: CEUR-WS
Place of Publication: Aachen
ISSN: 1613-0073
Abstract:We address the challenge of machine interpretation of subtle speech intonations that convey complex meanings. We assume that emotions and interrogative statements follow regular prosodic patterns, allowing us to create an unsupervised intonation template dictionary. These templates can then serve as encoding mechanisms for higher-level labels. We use piecewise interpolation of syllable-level formant features to create intonation templates and evaluate their effectiveness on three speech emotion recognition datasets and declarative-interrogative utterances. The results indicate that individual syllables can be detected for basic emotions with nearly double the accuracy of chance. Additionally, certain intonation templates exhibit a correlation with interrogative implications.
https://eprints.bournemouth.ac.uk/39773/
https://ceur-ws.org/Vol-3644/IJCLR2023_paper_31.pdf
Source: BURO EPrints