# Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data

arXiv: https://arxiv.org/abs/2603.07534 · HTML: https://mlsanity.com/paper/2603.07534/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Patching open-vocabulary models by interpolating weights](https://mlsanity.com/paper/2208.05592/) (2022)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [VoxLingua107: a Dataset for Spoken Language Recognition](https://mlsanity.com/paper/2011.12998/) (2020)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus](https://mlsanity.com/paper/2305.18802/) (2023)
- [Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context](https://mlsanity.com/paper/2309.08105/) (2023)
- [Better speech synthesis through scaling](https://mlsanity.com/paper/2305.07243/) (2023)
- [What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model](https://mlsanity.com/paper/2306.06524/) (2023)
- [IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS](https://mlsanity.com/paper/2409.05356/) (2024)
- [LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning](https://mlsanity.com/paper/2406.07969/) (2024)
- [MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion](https://mlsanity.com/paper/2409.09352/) (2024)
- [MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows](https://mlsanity.com/paper/2510.08392/) (2025)
- [Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe](https://mlsanity.com/paper/2508.01691/) (2025)
- [Scalable Controllable Accented TTS](https://mlsanity.com/paper/2508.07426/) (2025)
- [Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis](https://mlsanity.com/paper/2601.14417/) (2026)
- [Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora](https://mlsanity.com/paper/2505.16191/) (2025)
- [Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis](https://mlsanity.com/paper/2512.18699/) (2025)
- [LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech](https://mlsanity.com/paper/2506.00628/) (2025)

## Built on by (most cited first, 2 of 2)

- [Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning](https://mlsanity.com/paper/2609.29123/) (2026)
- [AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation](https://mlsanity.com/paper/2610.14479/) (2026)

## Abstract (arXiv)

Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model American-accented English due limited accented data. We propose textitAccent Vector, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. textitAccent Vector is derived by fine-tuning a TTS system on native speech of a different language (i.e. non-English) and computing task vectors capturing accent characteristics (i.e. in English). By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech. In addition, it generalizes beyond English, enabling accent control across multiple languages. Objective and human evaluations confirm the effectiveness of Accent Vector for fine-grained and compositional accent control.