High capacity speech steganography for the G723.1 coder based on quantised line spectral pairs interpolation and CNN auto-encoding

Abstract

Citació per a la versió publicada 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.

Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

“…Frequently, SER is similar to ASR but with a form recognition (FR) module. Additionally, ASR can be used in the SS domain, as a steganalytic process, to check the integrity of the speech [4,23].…”

“…. (15) Moving on, different frameworks, including [4,23,70] have utilized ASR principles as a steganalysis process and MOS-LQO as an assessment tool to check the integrity and/or the steganography quality-loss (SQ-Loss) between the original unprocessed speech and degraded speech version that has been passed through the steganography distorting system.…”