Article: Computer music sound signal synthesis and separation based on time-frequency cross domain feature selection Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.42 pp.47 - 71 Abstract: Amid digital music's growth, challenges like multi-track interference and noise robustness persist. Traditional single-domain analysis struggles with harmonic and transient details. We propose a computer music sound signal separation model (CMSSM-TFCFS), which includes an encoder with time-frequency cross-domain feature selection, a residual temporal convolution-based separator for long-term dependencies, and a decoder. It is jointly trained with an acoustic parameter synthesis model (APSM-NV) that uses a multilayer LSTM to predict clean acoustic features and a transformer-based vocoder for waveform generation. On a self-built dataset, the separation model achieves a signal-to-distortion ratio of 16.6 dB and a scale-invariant signal-to-noise ratio of 16.9 dB, improving baselines by 6.4% and 10.5%. By dynamically integrating time-frequency features and enabling end-to-end optimisation, this work offers a new paradigm for complex music signal processing, advancing support for music production and audio restoration, and promoting progress in digital music processing. Inderscience Publishers - linking academia, business and industry through research

Title: Computer music sound signal synthesis and separation based on time-frequency cross domain feature selection

Authors: Yanyan Wang

Addresses: School of Pre-school Education (School of Music), Lianyungang Normal University, Lianyungang, 222006, China

Abstract: Amid digital music's growth, challenges like multi-track interference and noise robustness persist. Traditional single-domain analysis struggles with harmonic and transient details. We propose a computer music sound signal separation model (CMSSM-TFCFS), which includes an encoder with time-frequency cross-domain feature selection, a residual temporal convolution-based separator for long-term dependencies, and a decoder. It is jointly trained with an acoustic parameter synthesis model (APSM-NV) that uses a multilayer LSTM to predict clean acoustic features and a transformer-based vocoder for waveform generation. On a self-built dataset, the separation model achieves a signal-to-distortion ratio of 16.6 dB and a scale-invariant signal-to-noise ratio of 16.9 dB, improving baselines by 6.4% and 10.5%. By dynamically integrating time-frequency features and enabling end-to-end optimisation, this work offers a new paradigm for complex music signal processing, advancing support for music production and audio restoration, and promoting progress in digital music processing.

Keywords: time-frequency cross-domain characteristics; sound signal processing; computer music; residual time convolution; neural vocoder; attention mechanism.

DOI: 10.1504/IJICT.2026.153382

International Journal of Information and Communication Technology, 2026 Vol.27 No.42, pp.47 - 71

Received: 28 Oct 2025
Accepted: 22 Jan 2026
Published online: 06 May 2026 *

Title: Computer music sound signal synthesis and separation based on time-frequency cross domain feature selection

Keep up-to-date