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

arXiv: https://arxiv.org/abs/2003.06686 · HTML: https://mlsanity.com/paper/2003.06686/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery](https://mlsanity.com/paper/2103.08199/) (2021)
- [It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system](https://mlsanity.com/paper/2105.00260/) (2021)
- [A learned conditional prior for the VAE acoustic space of a TTS system](https://mlsanity.com/paper/2106.10229/) (2021)
- [Location, Location: Enhancing the Evaluation of Text-to-Speech Synthesis Using the Rapid Prosody Transcription Paradigm](https://mlsanity.com/paper/2107.02527/) (2021)

## Abstract (arXiv)

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.