Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/146477
Title: High capacity speech steganography for the G723.1 coder based on quantised line spectral pairs interpolation and CNN auto-encoding
Author: Kheddar, Hamza
Megías Jiménez, David
Others: University of Medea
Universitat Oberta de Catalunya. Internet Interdisciplinary Institute (IN3)
CYBERCAT - Center for Cybersecurity Research of Catalonia
Keywords: auto-encoder
convolutional neural networks
multi-pulse maximum likelihood quantisation
G.723.1
speech steganography
interpolation
Issue Date: 6-Jan-2022
Publisher: Applied Intelligence
Citation: Kheddar, H., & Megías, D. (2022). High capacity speech steganography for the G723.1 coder based on quantised line spectral pairs interpolation and CNN auto-encoding. Applied Intelligence, 52(8), 9441-9459. doi: 10.1007/s10489-021-02938-7
Published in: 52;
Project identifier: info:eu-repo/grantAgreement/MICINN/RTI2018-095094-B-C22
info:eu-repo/grantAgreement/MICINN/PCI2020-120689-2
Abstract: In this paper, a novel steganographic method for Voice over IP applications -called Steganography-based Interpolation and Auto-Encoding (SIAE)- is proposed. The aim of the proposed scheme is to securely transmit a secret speech hidden within another (cover) speech coded with a G723.1 coder. SIAE embeds the steganograms in four interpolated and quantised line spectral pairs (QLSP) vectors. In order to minimize the changes in the cover speech, the proposed approach uses a 1D auto-encoder to compress the payload, and this scheme only requires embedding eight bits in about 30% of the packets. At the receiver side, the secret data can be successfully expanded to its original size upon decoding. This represents a significant reduction in the number of modified bits compared to state-of-the-art schemes, and results in enhanced undetectability and decreased steganographic quality loss. The results show that the proposed auto-encoder scheme has a very high performance since it can compress the embedded data up to 80 times from its original size, leading to a steganographic capacity that exceeds one kilobit per second (kpbs). In terms of imperceptibility, which is a relevant property for speech-in-speech steganography, the proposed SIAE method entails a very imperceptible distortion, with an average steganographic quality loss not greater than 0.19 in terms of mean opinion scores (MOS). Last but not least, the proposed method evades steganalysis specifically targeted at speech steganography. The tested steganalytic methods fail in detecting the steganographic content produced with the proposed SIAE method, yielding classification results that are indistinguishable from random guessing.
Language: English
URI: http://hdl.handle.net/10609/146477
ISSN: 0924-669XMIAR
Appears in Collections:Articles cientÍfics
Articles

Files in This Item:
File Description SizeFormat 
megias_ai_high.pdf1,04 MBAdobe PDFThumbnail
View/Open