AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911422856822784 |
|---|---|
| author | Zhong, Jinzuomu Richmond, Korin Su, Zhiba Sun, Siqi |
| author_facet | Zhong, Jinzuomu Richmond, Korin Su, Zhiba Sun, Siqi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09098 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AccentBox: Towards High-Fidelity Zero-Shot Accent Generation Zhong, Jinzuomu Richmond, Korin Su, Zhiba Sun, Siqi Sound Computation and Language Audio and Speech Processing 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. |
| title | AccentBox: Towards High-Fidelity Zero-Shot Accent Generation |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.09098 |