Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However, when learning to control prosody in text-to-speech voices, it is not clear what exactly the control is modifying. Existing research on discrete representation learning for prosody has demonstrated high naturalness, but no analysis has been performed on what these representations capture, or if they can generate meaningfully-distinct variants of an utterance. We present a phrase-level variational autoencoder with a multi-modal prior, using the mode centres as ‘intonation codes’. Our evaluation establishes which intonation codes are perceptually distinct, finding that the intonation codes from our multi-modal latent model were significantly more distinct than a baseline using k-means clustering. We carry out a follow-up qualitative study to determine what information the codes are carrying. Most commonly, listeners commented on the intonation codes having a statement or question style. However, many other affect-related styles were also reported, including: emotional, uncertain, surprised, sarcastic, passive aggressive, and upset. Finally, we lay out several methodological issues for evaluating distinct prosodies.
Original languageEnglish
Title of host publicationProceedings of Speech Prosody 2020
Publication statusPublished - 24 May 2020
EventSpeech Prosody 2020 - University of Tokyo, Tokyo, Japan
Duration: 24 May 202028 May 2020

Publication series

ISSN (Electronic)2333-2042


ConferenceSpeech Prosody 2020
Internet address

Keywords / Materials (for Non-textual outputs)

  • speech synthesis
  • prosody
  • speech perception
  • intonation modelling
  • machine learning
  • prosodic variation
  • discrete representation learning
  • variational autoencoder


Dive into the research topics of 'Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0'. Together they form a unique fingerprint.

Cite this