Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914701896581120 |
|---|---|
| author | Kanda, Naoyuki Wang, Xiaofei Eskimez, Sefik Emre Thakker, Manthan Yang, Hemin Zhu, Zirun Tang, Min Li, Canrun Tsai, Chung-Hsien Xiao, Zhen Xia, Yufei Li, Jinzhu Liu, Yanqing Zhao, Sheng Zeng, Michael |
| author_facet | Kanda, Naoyuki Wang, Xiaofei Eskimez, Sefik Emre Thakker, Manthan Yang, Hemin Zhu, Zirun Tang, Min Li, Canrun Tsai, Chung-Hsien Xiao, Zhen Xia, Yufei Li, Jinzhu Liu, Yanqing Zhao, Sheng Zeng, Michael |
| contents | Laughter is one of the most expressive and natural aspects of human speech, conveying emotions, social cues, and humor. However, most text-to-speech (TTS) systems lack the ability to produce realistic and appropriate laughter sounds, limiting their applications and user experience. While there have been prior works to generate natural laughter, they fell short in terms of controlling the timing and variety of the laughter to be generated. In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression. Specifically, ELaTE works on the audio prompt to mimic the voice characteristic, the text prompt to indicate the contents of the generated speech, and the input to control the laughter expression, which can be either the start and end times of laughter, or the additional audio prompt that contains laughter to be mimicked. We develop our model based on the foundation of conditional flow-matching-based zero-shot TTS, and fine-tune it with frame-level representation from a laughter detector as additional conditioning. With a simple scheme to mix small-scale laughter-conditioned data with large-scale pre-training data, we demonstrate that a pre-trained zero-shot TTS model can be readily fine-tuned to generate natural laughter with precise controllability, without losing any quality of the pre-trained zero-shot TTS model. Through objective and subjective evaluations, we show that ELaTE can generate laughing speech with significantly higher quality and controllability compared to conventional models. See https://aka.ms/elate/ for demo samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07383 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like Kanda, Naoyuki Wang, Xiaofei Eskimez, Sefik Emre Thakker, Manthan Yang, Hemin Zhu, Zirun Tang, Min Li, Canrun Tsai, Chung-Hsien Xiao, Zhen Xia, Yufei Li, Jinzhu Liu, Yanqing Zhao, Sheng Zeng, Michael Audio and Speech Processing Computation and Language Machine Learning Sound Laughter is one of the most expressive and natural aspects of human speech, conveying emotions, social cues, and humor. However, most text-to-speech (TTS) systems lack the ability to produce realistic and appropriate laughter sounds, limiting their applications and user experience. While there have been prior works to generate natural laughter, they fell short in terms of controlling the timing and variety of the laughter to be generated. In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression. Specifically, ELaTE works on the audio prompt to mimic the voice characteristic, the text prompt to indicate the contents of the generated speech, and the input to control the laughter expression, which can be either the start and end times of laughter, or the additional audio prompt that contains laughter to be mimicked. We develop our model based on the foundation of conditional flow-matching-based zero-shot TTS, and fine-tune it with frame-level representation from a laughter detector as additional conditioning. With a simple scheme to mix small-scale laughter-conditioned data with large-scale pre-training data, we demonstrate that a pre-trained zero-shot TTS model can be readily fine-tuned to generate natural laughter with precise controllability, without losing any quality of the pre-trained zero-shot TTS model. Through objective and subjective evaluations, we show that ELaTE can generate laughing speech with significantly higher quality and controllability compared to conventional models. See https://aka.ms/elate/ for demo samples. |
| title | Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like |
| topic | Audio and Speech Processing Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2402.07383 |