Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910045221945344 |
|---|---|
| author | Lertpetchpun, Thanathai Trachu, Thanapat Lee, Jihwan Feng, Tiantian Byrd, Dani Narayanan, Shrikanth |
| author_facet | Lertpetchpun, Thanathai Trachu, Thanapat Lee, Jihwan Feng, Tiantian Byrd, Dani Narayanan, Shrikanth |
| contents | 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 \textit{Accent Vector}, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. \textit{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07534 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data Lertpetchpun, Thanathai Trachu, Thanapat Lee, Jihwan Feng, Tiantian Byrd, Dani Narayanan, Shrikanth Computation and Language 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 \textit{Accent Vector}, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. \textit{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. |
| title | Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.07534 |