Wmcodec: End-to-end Neural Speech Codec With Deep Watermarking For Authenticity Verification

Abstract

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

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyzhou2024wmcodec

Related papers

• Audio Codec Augmentation For Robust Collaborative Watermarking Of Speech Synthesis (2024)4.52
• Multiplexing Neural Audio Watermarks (2025)0.00
• Collaborative Watermarking For Adversarial Speech Synthesis (2023)0.00
• P2mark: Plug-and-play Parameter-level Watermarking For Neural Speech Generation (2025)0.00
• Detection Of Doctored Speech: Towards An End-to-end Parametric Learn-able Filter Approach (2022)0.00
• Spatialcodec: Neural Spatial Speech Coding (2023)3.69
• A Neural Speech Codec For Noise Robust Speech Coding (2023)0.00
• AWARE: Audio Watermarking With Adversarial Resistance To Edits (2025)0.00