# High-Fidelity Neural Phonetic Posteriorgrams

arXiv: https://arxiv.org/abs/2402.17735 · HTML: https://mlsanity.com/paper/2402.17735/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2024.

## Built on by (most cited first, 9 of 9)

- [Pairwise Evaluation of Accent Similarity in Speech Synthesis](https://mlsanity.com/paper/2505.14410/) (2025)
- [Rethinking Discrete Speech Representation Tokens for Accent Generation](https://mlsanity.com/paper/2601.19786/) (2026)
- [CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data](https://mlsanity.com/paper/2602.19166/) (2026)
- [Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoring](https://mlsanity.com/paper/2607.13721/) (2026)
- [Residual Tokens Enhance Masked Autoencoders for Speech Modeling](https://mlsanity.com/paper/2601.19399/) (2026)
- [Controllable Accent Normalization via Discrete Diffusion](https://mlsanity.com/paper/2603.14275/) (2026)
- [UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling](https://mlsanity.com/paper/2606.31128/) (2026)
- [TokAN: Accent Normalization Using Self-Supervised Speech Tokens](https://mlsanity.com/paper/2607.03928/) (2026)
- [Adapting Diffusion-Based Music Synthesis to Speech and Singing Voice Conversion](https://mlsanity.com/paper/2607.13278/) (2026)

## Abstract (arXiv)

A phonetic posteriorgram (PPG) is a time-varying categorical distribution over acoustic units of speech (e.g., phonemes). PPGs are a popular representation in speech generation due to their ability to disentangle pronunciation features from speaker identity, allowing accurate reconstruction of pronunciation (e.g., voice conversion) and coarse-grained pronunciation editing (e.g., foreign accent conversion). In this paper, we demonstrably improve the quality of PPGs to produce a state-of-the-art interpretable PPG representation. We train an off-the-shelf speech synthesizer using our PPG representation and show that high-quality PPGs yield independent control over pitch and pronunciation. We further demonstrate novel uses of PPGs, such as an acoustic pronunciation distance and fine-grained pronunciation control.