Multi-attention bottleneck for gated convolutional encoder-decoder-based speech enhancement

• Main Authors: Saleem, Nasir, Gunawan, Teddy Surya, Shafi, Muhammad, Bourouis, Sami, Trigui, Aymen
• Format: Article
• Language: English; English
• Published: IEEE 2023
• Subjects: TK7885 Computer engineering
• Online Access: http://irep.iium.edu.my/108080/7/108080_Multi-attention%20bottleneck%20for%20gated%20convolutional%20encoder_SCOPUS.pdf; http://irep.iium.edu.my/108080/8/108080_Multi-attention%20bottleneck%20for%20gated%20convolutional%20encoder.pdf; http://irep.iium.edu.my/108080/; https://ieeexplore.ieee.org/abstract/document/10283829

Convolutional encoder-decoder (CED) has emerged as a powerful architecture, particularly in speech enhancement (SE), which aims to improve the intelligibility and quality and intelligibility of noise-contaminated speech. This architecture leverages the strength of the convolutional neural networks (...