实现跨语言口音强度可控的语音合成，让声音既保个性又可调口音浓淡。
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
- 分离说话人与口音表征，通过加权语言嵌入调控口音强度。
- 在印地语等低资源语言上口音相似度提升12.3%，自然度更佳。
- 适合需要精细控制口音的多语言语音合成应用。
口音转换与可控性仍是跨语言文本转语音（TTS）的核心挑战，尤其在低资源且语音差异大的印度语言中。尽管基于大语言模型（LLM）的TTS系统具备强跨语言泛化能力，但对口音特征和强度的显式控制有限。本文提出CrossAccent-TTS框架，实现口音控制与转换的同时保持说话人身份。具体地，引入口音强度控制器（AIC），将加权语言嵌入注入口音子空间，支持口音间的平滑插值和推理时细粒度调节口音强度。在Indic Multilingual和L2-Arctic数据集上的实验表明，CrossAccent-TTS在口音相似度和可控性上优于强基线，同时保持说话人相似性和语音自然度。
原文摘要 · Abstract (English)
Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-speech (TTS), particularly for low-resource and phonetically diverse Indic languages. While recent large language model (LLM)-based TTS systems exhibit strong cross-lingual generalization, they provide limited explicit control over accent characteristics and intensity. In this paper, we propose CrossAccentTTS, a framework that enables both accent control and conversion while preserving speaker identity. Specifically, we introduce an Accent Intensity Controller (AIC) that injects weighted language embeddings into the accent subspace, allowing smooth interpolation between accents and fine-grained modulation of accent strength at inference time. Experiments on the Indic Multilingual and L2-arctic datasets shows that CrossAccent-TTS achieves precise control of accent intensity, outperforming strong baselines in accent similarity and controllability by maintaining speaker similarity and naturalness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。