# Hide and Speak: Towards Deep Neural Networks for Speech Steganography

arXiv: https://arxiv.org/abs/1902.03083 · HTML: https://mlsanity.com/paper/1902.03083/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 5 of 5)

- [A Brief Survey on Deep Learning Based Data Hiding](https://mlsanity.com/paper/2103.01607/) (2021)
- [THInImg: Cross-modal Steganography for Presenting Talking Heads in Images](https://mlsanity.com/paper/2311.17177/) (2023)
- [Towards Robust Image-in-Audio Deep Steganography](https://mlsanity.com/paper/2303.05007/) (2023)
- [WavInWav: Time-domain Speech Hiding via Invertible Neural Network](https://mlsanity.com/paper/2510.02915/) (2025)
- [A Training-Free Proactive Defense Against Partial Speech Manipulation via Self-Embedding Steganography](https://mlsanity.com/paper/2608.25285/) (2026)

## Abstract (arXiv)

Steganography is the science of hiding a secret message within an ordinary public message, which is referred to as Carrier. Traditionally, digital signal processing techniques, such as least significant bit encoding, were used for hiding messages. In this paper, we explore the use of deep neural networks as steganographic functions for speech data. We showed that steganography models proposed for vision are less suitable for speech, and propose a new model that includes the short-time Fourier transform and inverse-short-time Fourier transform as differentiable layers within the network, thus imposing a vital constraint on the network outputs. We empirically demonstrated the effectiveness of the proposed method comparing to deep learning based on several speech datasets and analyzed the results quantitatively and qualitatively. Moreover, we showed that the proposed approach could be applied to conceal multiple messages in a single carrier using multiple decoders or a single conditional decoder. Lastly, we evaluated our model under different channel distortions. Qualitative experiments suggest that modifications to the carrier are unnoticeable by human listeners and that the decoded messages are highly intelligible.