WMCodec：面向真实性验证的端到端神经语音编解码器与深度水印
WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
AI总结：
本文提出WMCodec，首个端到端联合训练语音压缩重建与水印嵌入提取的神经语音编解码器，通过迭代式注意力印记单元深度融合水印与语音特征，在6 kbps带宽和16 bps容量下实现常见攻击下超过99%的水印提取精度，兼顾不可感知性与鲁棒性。
摘要：
近年来语音伪造的进展要求在神经语音编解码器中建立更强的验证机制以确保真实性。现有方法在压缩前嵌入数值水印，并从重建语音中提取水印进行验证，但存在水印与编解码器分离训练、跨模态信息融合不足等局限，导致水印不可感知性、提取精度和容量下降。为解决这些问题，我们提出WMCodec，这是首个以端到端方式联合训练压缩重建与水印嵌入提取的神经语音编解码器，同时优化水印的不可感知性和可提取性。此外，我们设计了一种迭代式注意力印记单元（AIU），用于更深层地融合水印与语音特征，降低量化噪声对水印的影响。实验结果表明，WMCodec在大多数水印不可感知性质量指标上优于AudioSeal与Encodec的组合，并且在水印提取精度上持续超过AudioSeal与Encodec的组合以及增强型TraceableSpeech。在6 kbps带宽和16 bps水印容量下，WMCodec在常见攻击下保持超过99%的提取精度，展现出强大的鲁棒性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
