TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912119856824320 |
|---|---|
| author | Zhou, Junzuo Yi, Jiangyan Wang, Tao Tao, Jianhua Bai, Ye Zhang, Chu Yuan Ren, Yong Wen, Zhengqi |
| author_facet | Zhou, Junzuo Yi, Jiangyan Wang, Tao Tao, Jianhua Bai, Ye Zhang, Chu Yuan Ren, Yong Wen, Zhengqi |
| contents | Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a process that hurts both speech quality and watermark imperceptibility. In addition, these approaches are limited in robustness and flexibility. To address these problems, we propose TraceableSpeech, a novel TTS model that directly generates watermarked speech, improving watermark imperceptibility and speech quality. Furthermore, We design the frame-wise imprinting and extraction of watermarks, achieving higher robustness against resplicing attacks and temporal flexibility in operation. Experimental results show that TraceableSpeech outperforms the strong baseline where VALL-E or HiFicodec individually uses WavMark in watermark imperceptibility, speech quality and resilience against resplicing attacks. It also can apply to speech of various durations. The code is avaliable at https://github.com/zjzser/TraceableSpeech |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04840 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking Zhou, Junzuo Yi, Jiangyan Wang, Tao Tao, Jianhua Bai, Ye Zhang, Chu Yuan Ren, Yong Wen, Zhengqi Sound Audio and Speech Processing Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a process that hurts both speech quality and watermark imperceptibility. In addition, these approaches are limited in robustness and flexibility. To address these problems, we propose TraceableSpeech, a novel TTS model that directly generates watermarked speech, improving watermark imperceptibility and speech quality. Furthermore, We design the frame-wise imprinting and extraction of watermarks, achieving higher robustness against resplicing attacks and temporal flexibility in operation. Experimental results show that TraceableSpeech outperforms the strong baseline where VALL-E or HiFicodec individually uses WavMark in watermark imperceptibility, speech quality and resilience against resplicing attacks. It also can apply to speech of various durations. The code is avaliable at https://github.com/zjzser/TraceableSpeech |
| title | TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.04840 |