Analysis and synthesis of intonation using the Tilt model.

By Paul A. Taylor. Journal of the Acoustical Society of America, 2000

412 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/77f807b546533e262067661c97d47799d945722c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Intent transfer in speech-to-speech machine translation (2012, background): “, duration and tilt amplitude) are positively correlated [21].”
Speech melody as articulatorily implemented communicative functions (2005, methodology): “The main examples of this group of models are the IPO model ( t Hart et al., 1990), the tilt model (Taylor, 2000), the quadratic spline model (Hirst and Espesser, 1993), and the Pierrehumbert model (Pierrehumbert, 1981).”
Predictability Effects on Durations of Content and Function Words in Conversational English (2009, methodology): “Intonational accent and phrasing has been transcribed for about one-third of the ICSI corpus by Taylor, using the Tilt conventions (Taylor, 2000), and by Ostendorf and colleagues, using a variant of the ToBI labelling system (Ostendorf, Shafran, Shattuck-Hufnagel, Byrne, & Carmichael, 2001).”
Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion Detection (2009, positive): “tour parameterization called Tilt Intonation Model [31].”
A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural $F_0$ Model for Statistical Parametric Speech Synthesis (2020, background): “VAE framework because the quantized latent codes are more compatible with the linguistic assumption that F0 can be abstracted as discretized prosodic events [40], [41].”
Automatic Building of Synthetic Voices from Audio Books (2010, background): “– What is an appropriate representation of intonation contours? For example, TILT is a model of intonation that represents intonation as a sequence of continuously parameterized intonation events [Taylor, 2000].”
Information Structure and the Syntax-Phonology Interface (2000, background): “…and Hirschberg 1990, Bartels 1997), and various notions of information structure or packaging (Halliday 1967a, Jackendoff 1972, Schmerling 1976, Ladd 1980, 1996, Gussenhoven 1983, Selkirk 1984, Terken 1984, Terken and Hirschberg 1994, Morel 1995, Rochemont 1986, Steedman 1991a,b, Zubizarreta 1998).”