ToBI or not toBI?
By Colin W. Wightman. 2002
In the decade that has passed since the introduction of the ToBI system for the transcription of prosody, speech technology has moved out of the laboratory and into commercial applications on several fronts. However, virtually none of the commercial products have made large-scale use of prosody. Nevertheless, researchers in both recognition and synthesis continue to agree that better utilization of prosody is essential to improving the performance and acceptability of commercial systems. In this paper, we review the current state of prosody in commercial systems, and examine how the ongoing discussions related to what and how to transcribe with respect to prosody have simultaneously advanced and inhibited the field. In particular, we argue that, in hindsight, the ToBI system contains several flaws that have limited its acceptance and application.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, background): “The challenges of annotation often require domain experts,however, and inter-rater annotations can differ substantially (Wightman, 2002).”
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (2018, background): “However, AuToBI still needs annotations for training, and ToBI, as a hand-designed label system, is known to have limited performance (Wightman, 2002).”
- Robust and Fine-grained Prosody Control of End-to-end Speech Synthesis (2018, background): “Problems were reported about hand annotations, and the cost was high [8].”
- The role of intonation in emotional expressions (2005, background): “(c) The subjectivity of the coding of perceived pitch is likely to lead to low inter-coder reliabilities (on this issue, see Syrdal and McGory, 2000; Wightman , 2002).”