NAS-TasNet: Neural Architecture Search for Time-Domain Speech Separation

NAS-TasNet: Neural Architecture Search for Time-Domain Speech Separation

The fully convolutional time-domain speech separation network (Conv-TasNet) has been used as a backbone model in various studies because of its structural excellence. To maximize the performance and efficiency of Conv-TasNet, we attempt to apply a neural architecture search (NAS). NAS is a branch of...

Full description

Bibliographic Details
Main Authors: Joo-Hyun Lee, Joon-Hyuk Chang, Jae-Mo Yang, Han-Gil Moon
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Automated machine learning (AutoML)
convolutional neural network (CNN)
deep learning
end-to-end
speech processing
speech separation
Online Access:https://ieeexplore.ieee.org/document/9777717/

Internet

https://ieeexplore.ieee.org/document/9777717/

Similar Items