Abstract
While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world’s over 6,000 spoken languages. In this work, we bring together the tasks of zero-shot voice cloning and multilingual low-resource TTS. Using the language agnostic meta learning (LAML) procedure and modifications to a TTS encoder, we show that it is possible for a system to learn speaking a new language using just 5 minutes of training data while retaining the ability to infer the voice of even unseen speakers in the newly learned language. We show the success of our proposed approach in terms of intelligibility, naturalness and similarity to target speaker using objective metrics as well as human studies and provide our code and trained models open source.- Anthology ID:
- 2022.aacl-main.56
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 741–751
- Language:
- URL:
- https://aclanthology.org/2022.aacl-main.56
- DOI:
- Cite (ACL):
- Florian Lux, Julia Koch, and Ngoc Thang Vu. 2022. Low-Resource Multilingual and Zero-Shot Multispeaker TTS. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 741–751, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Low-Resource Multilingual and Zero-Shot Multispeaker TTS (Lux et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.aacl-main.56.pdf