cs.SDJul 23, 2026

Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness

Authors: Zi HuHoumin SunLinxi LiYechen WangLiwei JinCarsten MapleMing Li

Organizations: Digital Innovation Research Center, Duke Kunshan University, Kunshan, China · OfSpectrum, Inc., Los Angeles, USA · University of Warwick, Coventry, United Kingdom · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China

Abstract

Neural audio codecs are challenging transformations for audio watermarking because they re-encode, quantize, and resynthesize speech. This paper investigates continuous latent-space watermarking for codec robustness. Instead of adding a watermark only to the waveform or spectrogram, we embed a 32-bit message into the continuous latent representation of a codec-like speech autoencoder. The pipeline uses a SEANet-style encoder-decoder, a Conformer-based message embedder, RVQ-guided latent decomposition, and a latent-domain detector trained under signal-processing and neural-codec transformations. Rather than proposing a final universal watermarking baseline, we characterize the trade-offs that appear when the watermark carrier is moved before neural decoding. On 48 kHz speech, EnCodec-aware training improves EnCodec-24k bit accuracy from 78.8% to 95.6% and 97.1%, while PESQ decreases from 3.727 to 3.514 and 3.427.

Explore similar work

CardsList
  1. Latent Audio Watermarking for Robustness to Neural Codec Resynthesis

    Sep 22, 2026Lovro Brulec, Sahil Karawade, Leonard KinzingerNeural Audio Codecs