# Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training

Source: [Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training](<https://www.sota2.com/research/paper/69ba31b30636e5bf4afc0a53>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-18T05:00:05.624Z

Authors: Houmin Sun, Zi Hu, Linxi Li, Yechen Wang, Liwei Jin, Carsten Maple, Ming Li

Published: 2026-03-17T17:09:45.000Z

## Abstract

Modern audio is created by mixing stems from different sources, raising the question: can we independently watermark each stem and recover all watermarks after separation? We study a separation-first, multi-stream watermarking framework --embedding distinct information into stems using unique keys but a shared structure, mixing, separating, and decoding from each output. A naive pipeline (robust watermarking + off-the-shelf separation) yields poor bit recovery, showing robustness to generic distortions does not ensure robustness to separation artifacts. To enable this, we study separation-aware watermarking in a controlled verification pipeline, where the separator is part of the detector and can be selected or optimized together with the watermarking system. Experiments on speech+music and vocal+accompaniment mixtures show substantial gains in post-separation recovery while maintaining perceptual quality.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Audio Watermark Decoding on Speech + Music Scenarios](<https://www.sota2.com/research/sota/audio-watermark-decoding-on-speech-plus-music-scenarios.md>): Audio Watermark Decoding; Speech + Music Scenarios; BER (Origin): 0.43.

- [Audio Watermark Decoding on Vocal + Accompaniment Scenarios](<https://www.sota2.com/research/sota/audio-watermark-decoding-on-vocal-plus-accompaniment-scenarios.md>): Audio Watermark Decoding; Vocal + Accompaniment Scenarios; Bit Error Rate (BER) - Origin: 1.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.16805>)

[PDF](<https://arxiv.org/pdf/2603.16805.pdf>)
