MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech

TL;DR

MelShield is a novel audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain, enabling reliable attribution and copyright protection without retraining TTS models.

Contribution

It introduces a plug-and-play, keyed spread-spectrum watermarking method operating during speech synthesis, enhancing robustness and scalability for AI-generated audio attribution.

Findings

Achieves near 100% watermark extraction accuracy under distortions.

Maintains high perceptual audio quality after watermark embedding.

Does not require retraining of existing TTS vocoders.

Abstract

In this paper, we propose MelShield, a robust, in-generation, keyed audio watermarking framework that embeds identifiable signals into AI-generated audio for copyright protection and reliable attribution. Specifically, MelShield operates in the Mel-spectrogram domain during the generation process, targeting intermediate acoustic representations in Mel-conditioned pipelines for text-to-speech (TTS) generation. The core idea is to treat the intermediate Mel-spectrogram as the host signal and embed a short binary payload via low-energy, keyed spread-spectrum perturbations distributed across carefully selected time-frequency regions prior to waveform synthesis. By performing watermarking before vocoder inference, MelShield remains plug-and-play for Mel-conditioned TTS architectures and does not require modification or retraining of the underlying TTS generation vocoder, such as DiffWave and HiFi-GAN. Moreover, the multi-user keyed construction enables scalable user-specific attribution, while the keyed verification mechanism limits unauthorized decoding, thereby reducing the risk of large-scale extractor probing and adversarial analysis. Extensive experiments on DiffWave and HiFi-GAN demonstrate that MelShield achieves reliable watermark extraction, approaching 100\% bit accuracy, even under signal distortions, e.g., compression and additive noise, while preserving high perceptual audio quality.