口音向量：无需口音数据的多语言TTS可控口音操控

摘要

口音作为社会结构的重要组成部分，既折射出多元文化特征，也塑造着个体的身份表达方式。尽管全球多数英语使用者为非母语人士，当前文本转语音系统却因缺乏口音数据而主要模拟美式英语发音。我们提出"口音向量"这一可控表征方法，可在无需口音训练数据的前提下实现多语言TTS系统中的口音操控。该向量通过在不同语言的母语语音上微调TTS模型，并计算捕捉口音特征的任务向量（以英语为例）而得。通过缩放与插值处理，我们实现了对口音强度的细粒度控制，并能生成混合口音语音。此外，该方法具备跨语言泛化能力，可在多语言场景下实现口音控制。客观评估与人工测评结果共同验证了口音向量在细粒度及组合式口音控制方面的有效性。

English

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 Accent Vector, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. Accent 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.

口音向量：无需口音数据的多语言TTS可控口音操控

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

摘要

Support