An Automatic Mixing Speech Enhancement System for Information Integrity

Liu X, Ai H, Reiss JD. An Automatic Mixing Speech Enhancement System for Information Integrity. J Audio Eng Soc. 2025;73(10):648-659. doi:10.17743/jaes.2022.0222

@article{Liu2025_23027,
  author = {Liu, Xiaojing and Ai, Hongwei and Reiss, Joshua D.},
  title = {{An Automatic Mixing Speech Enhancement System for Information Integrity}},
  journal = {Journal of the Audio Engineering Society},
  volume = {73},
  number = {10},
  pages = {648--659},
  year = {2025},
  month = oct,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2022.0222},
  url = {https://doi.org/10.17743/jaes.2022.0222}
}

TY  - JOUR
TI  - An Automatic Mixing Speech Enhancement System for Information Integrity
AU  - Liu, Xiaojing
AU  - Ai, Hongwei
AU  - Reiss, Joshua D.
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 73
IS  - 10
SP  - 648
EP  - 659
PY  - 2025
DA  - 2025/10/01
DO  - 10.17743/jaes.2022.0222
UR  - https://doi.org/10.17743/jaes.2022.0222
PB  - Audio Engineering Society
LA  - en
AB  - The simultaneous presence of multiple audio signals can lead to information loss due to auditory masking and interference, often resulting in diminished signal clarity. The authors propose a speech enhancement system designed to present multiple tracks of speech information with reduced auditory masking, thereby enabling more effective discernment of multiple simultaneous talkers. The system evaluates auditory masking using the ITU-R BS.1387 Perceptual Evaluation of Audio Quality model along with ideal mask ratio metrics. To achieve optimal results, a combined iterative Harmony Search algorithm and integer optimization are employed, applying audio effects such as level balancing, equalization, dynamic range compression, and spatialization, aimed at minimizing masking. Objective and subjective listening tests demonstrate that the proposed system performs competitively against mixes created by professional sound engineers and surpasses existing automixing systems. This system is applicable in various communication scenarios, including teleconferencing, in-game voice communication, and live streaming.
ER  -