mlsanityData to 7 Oct 2026

AccentBox: Towards High-Fidelity Zero-Shot Accent Generation

arXiv 2409.09098 ↗First posted 13 Sep 2024cs.SD cs.CL eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identification (AID) with 0.56 f1 score on unseen speakers. In the second stage, we condition a ZS-TTS system on the pretrained speaker-agnostic accent embeddings extracted by the AID model. The proposed system achieves higher accent fidelity on inherent/cross accent generation, and enables unseen accent generation.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

19 of 39 references.

References · 19

  1. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  3. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  5. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  6. 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
  7. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  8. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  9. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  10. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 167
  11. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 119
  12. 2023LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpuscited by 100
7 more
  1. 2024Natural language guidance of high-fidelity text-to-speech with synthetic annotationscited by 66
  2. 2023The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASRcited by 36
  3. 2021The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methodscited by 24
  4. 2023CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voicecited by 19
  5. 2023Accented Text-to-Speech Synthesis with Limited Datacited by 12
  6. 2022Explicit Intensity Control for Accented Text-to-speechcited by 5
  7. 2023Accent-VITS:accent transfer for end-to-end TTScited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesiscited by 39
  2. 2025Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globecited by 5
  3. 2025Pairwise Evaluation of Accent Similarity in Speech Synthesiscited by 4
  4. 2026Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesiscited by 4
  5. 2026Rethinking Discrete Speech Representation Tokens for Accent Generationcited by 2
  6. 2026An Evaluation Framework for Text-to-Speech Voice Reconstructioncited by 1
  7. 2026Synthetic Audio Generation Framework for Air Traffic Control Speech Recognitioncited by 0
  8. 2026Flexible and Interpretable Accent Distance Measurementscited by 0
  9. 2026A Cross Community Agenda for Speech AIcited by 0