English

Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement

Computation and Language 2025-06-23 v1 Sound Audio and Speech Processing

Abstract

We propose a first streaming accent conversion (AC) model that transforms non-native speech into a native-like accent while preserving speaker identity, prosody and improving pronunciation. Our approach enables stream processing by modifying a previous AC architecture with an Emformer encoder and an optimized inference mechanism. Additionally, we integrate a native text-to-speech (TTS) model to generate ideal ground-truth data for efficient training. Our streaming AC model achieves comparable performance to the top AC models while maintaining stable latency, making it the first AC system capable of streaming.

Keywords

Cite

@article{arxiv.2506.16580,
  title  = {Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement},
  author = {Tuan-Nam Nguyen and Ngoc-Quan Pham and Seymanur Akti and Alexander Waibel},
  journal= {arXiv preprint arXiv:2506.16580},
  year   = {2025}
}

Comments

Accepted to INTERSPEECH 2025

R2 v1 2026-07-01T03:25:39.863Z