Time domain speech enhancement with CNN and time-attention transformer

• المؤلفون الرئيسيون: Saleem, Nasir, Gunawan, Teddy Surya, Dhahbi, Sami, Bourouis, Sami
• التنسيق: مقال
• اللغة: English; English
• منشور في: Elsevier 2024
• الموضوعات: TK7885 Computer engineering
• الوصول للمادة أونلاين: http://irep.iium.edu.my/111097/2/111097_Time%20domain%20speech%20enhancement%20with%20CNN_SCOPUS.pdf; http://irep.iium.edu.my/111097/3/111097_Time%20domain%20speech%20enhancement%20with%20CNN.pdf; http://irep.iium.edu.my/111097/; https://www.sciencedirect.com/science/article/abs/pii/S1051200424000332?via%3Dihub; https://doi.org/10.1016/j.dsp.2024.104408

Speech enhancement in the time domain involves improving the quality and intelligibility of noisy speech by processing the waveform directly without the need for explicit feature extraction or domain transformation. Deep learning is a powerful approach for time domain speech enhancement, offering si...