WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912169708224512 |
|---|---|
| author | Zhou, Junzuo Yi, Jiangyan Ren, Yong Tao, Jianhua Wang, Tao Zhang, Chu Yuan |
| author_facet | Zhou, Junzuo Yi, Jiangyan Ren, Yong Tao, Jianhua Wang, Tao Zhang, Chu Yuan |
| contents | Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and watermark embedding-extraction in an end-to-end manner, optimizing both imperceptibility and extractability of the watermark. Furthermore, We design an iterative Attention Imprint Unit (AIU) for deeper feature integration of watermark and speech, reducing the impact of quantization noise on the watermark. Experimental results show WMCodec outperforms AudioSeal with Encodec in most quality metrics for watermark imperceptibility and consistently exceeds both AudioSeal with Encodec and reinforced TraceableSpeech in extraction accuracy of watermark. At bandwidth of 6 kbps with a watermark capacity of 16 bps, WMCodec maintains over 99% extraction accuracy under common attacks, demonstrating strong robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12121 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification Zhou, Junzuo Yi, Jiangyan Ren, Yong Tao, Jianhua Wang, Tao Zhang, Chu Yuan Sound Audio and Speech Processing Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and watermark embedding-extraction in an end-to-end manner, optimizing both imperceptibility and extractability of the watermark. Furthermore, We design an iterative Attention Imprint Unit (AIU) for deeper feature integration of watermark and speech, reducing the impact of quantization noise on the watermark. Experimental results show WMCodec outperforms AudioSeal with Encodec in most quality metrics for watermark imperceptibility and consistently exceeds both AudioSeal with Encodec and reinforced TraceableSpeech in extraction accuracy of watermark. At bandwidth of 6 kbps with a watermark capacity of 16 bps, WMCodec maintains over 99% extraction accuracy under common attacks, demonstrating strong robustness. |
| title | WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.12121 |