mlsanityData to 7 Oct 2026

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

arXiv 2603.07534 ↗First posted 8 Mar 2026cs.CLcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

31 of 45 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  6. 2022Editing Models with Task Arithmeticcited by 1,076
  7. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  8. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 381
  9. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  10. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  11. 2024LoRA Learns Less and Forgets Lesscited by 313
  12. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
19 more
  1. 2022Patching open-vocabulary models by interpolating weightscited by 187
  2. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
  3. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 119
  4. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 118
  5. 2023LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpuscited by 100
  6. 2023Libriheavy: a 50,000 hours ASR corpus with punctuation casing and contextcited by 84
  7. 2023Better speech synthesis through scalingcited by 63
  8. 2023What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Modelcited by 18
  9. 2024LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioningcited by 15
  10. 2024IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTScited by 15
  11. 2024MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversioncited by 6
  12. 2025Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globecited by 5
  13. 2025MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flowscited by 5
  14. 2025Scalable Controllable Accented TTScited by 4
  15. 2026Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesiscited by 4
  16. 2025Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corporacited by 3
  17. 2025Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesiscited by 2
  18. 2025LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speechcited by 1
  19. 2025Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Controlcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloningcited by 0