The tilt intonation model

By Paul A. Taylor. 1998

The tilt intonation model facilitates automatic analysis and synthesis of intonation. The analysis algorithm detects intonational events in F0 contours and parameterises them in terms of the continuously varying Tilt parameters. We describe the analysis system and give results for speaker independent spontaneous dialogue speech. We then describe a synthesis algorithm which can generate F0 contours given a tilt parameterisation of an utterance. We give results showing how well the automatically produced contours match natural ones. The paper concludes with a discussion of the linguistic relevance of the tilt parameters and show that this is both a useful and natural way of representing intonation.

How researchers see this paper

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

1. Xu Tan
2. Tao Qin
3. Frank K. Soong
4. Tie-Yan Liu
5. Yi Ren
6. Wei-Ning Hsu
7. Ye Jia
8. Eric Battenberg

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “For example, the prosody information can be labeled according to some annotation schemas, such as ToBI [301], AuToBI [288], Tilt [339], INTSINT [109], and SLAM [243].”
• Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, methodology): “Numerous works have explored annotation schemes for diagramming and automatic labeling of prosody: ToBi (Silverman et al., 1992), AuToBI (Rosenberg, 2010), Tilt (Taylor, 1998), INTSINT (Hirst, 2001), SLAM (Obin et al., 2014) all describe methods for the annotation and automatic extraction of labels ”
• Predicting Expressive Speaking Style from Text in End-To-End Speech Synthesis (2018, methodology): “INTSINT [3], ToBi [4], Momel [5], landmark detection [6], Tilt [7], and SLAM [8] all describe methods to annotate or classify prosodic features such as breaks, intonation, rhythm, and melody.”
• SLAM: Automatic Stylization and Labelling of Speech Melody (2014, background): “to a small set of parameters that are used to describe slowly time-varying F0 variations [18, 19, 20, 21].”
• Exploiting Acoustic and Syntactic Features for Prosody Labeling in a Maximum Entropy Framework (2007, methodology): “Such an n-gram model of quantized continuous features is similar to representing the set of features with a linear fit as done in the tilt intonational model (Taylor, 1998).”