# TTS-Guided Training for Accent Conversion Without Parallel Data

arXiv: https://arxiv.org/abs/2212.10204 · HTML: https://mlsanity.com/paper/2212.10204/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2022.

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

- [Convert and Speak: Zero-shot Accent Conversion with Minimum Supervision](https://mlsanity.com/paper/2408.10096/) (2024)
- [Transfer the linguistic representations from TTS to accent conversion with non-parallel data](https://mlsanity.com/paper/2401.03538/) (2024)
- [Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS](https://mlsanity.com/paper/2410.14997/) (2024)
- [Pairwise Evaluation of Accent Similarity in Speech Synthesis](https://mlsanity.com/paper/2505.14410/) (2025)
- [DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech](https://mlsanity.com/paper/2410.13342/) (2024)
- [Non-autoregressive real-time Accent Conversion model with voice cloning](https://mlsanity.com/paper/2405.13162/) (2024)
- [CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data](https://mlsanity.com/paper/2602.19166/) (2026)
- [Controllable Accent Normalization via Discrete Diffusion](https://mlsanity.com/paper/2603.14275/) (2026)
- [TokAN: Accent Normalization Using Self-Supervised Speech Tokens](https://mlsanity.com/paper/2607.03928/) (2026)

## Abstract (arXiv)

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a novel accent conversion framework without the need of parallel data. Specifically, a text-to-speech (TTS) system is first pretrained with target-accented speech data. This TTS model and its hidden representations are expected to be associated only with the target accent. Then, a speech encoder is trained to convert the accent of the speech under the supervision of the pretrained TTS model. In doing so, the source-accented speech and its corresponding transcription are forwarded to the speech encoder and the pretrained TTS, respectively. The output of the speech encoder is optimized to be the same as the text embedding in the TTS system. At run-time, the speech encoder is combined with the pretrained TTS decoder to convert the source-accented speech toward the target. In the experiments, we converted English with two source accents (Chinese and Indian) to the target accent (American/British/Canadian). Both objective metrics and subjective listening tests successfully validate that, without any parallel data, the proposed approach generates speech samples that are close to the target accent with high speech quality.