Complex-valued temporal convolutional network for speech enhancement

DOI10.1142/S0219691324500152MaRDI QIDQ6591726zbMATH OpenFDO

Authors Jiaqi Song, Lian Zou, Liqing Zhou, Ziao Liu, Cien Fan, Bin Wang

Publication date 22 August 2024

Published in International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S0219691324500152

zbMATH Keywords

complex-valued spectrogramspeech enhancementTCN

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Improving speech enhancement in unseen noise using deep convolutional neural network
• Speech enhancement with noise estimation and filtration using deep learning models
• Application of perceptual filtering models to noisy speech signals enhancement
• Single channel source separation using time-frequency non-negative matrix factorization and sigmoid base normalization deep neural networks
• Speech enhancement for non-stationary noise environments

This page was built for publication: Complex-valued temporal convolutional network for speech enhancement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6591726)