Idanet: An information distillation and aggregation network for speech enhancement

W Tai, T Lan, Q Wang, Q Liu - IEEE Signal Processing Letters, 2021 - ieeexplore.ieee.org
Speech enhancement aims to restore clean speech from noisy environments. In recent
years, skip connections have shown great promise in improving speech enhancement …

Improving monaural speech enhancement with dynamic scene perception module

T Lan, J Li, W Tai, C Chen, J Kang… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Speech enhancement aims to recover clean speech from complex noise backgrounds. This
paper proposes a novel information processing module dubbed dynamic scene perception …

Foster strengths and circumvent weaknesses: a speech enhancement framework with two-branch collaborative learning

W Tai, J Li, Y Wang, T Lan, Q Liu - arXiv preprint arXiv:2110.05713, 2021 - arxiv.org
Recent single-channel speech enhancement methods usually convert waveform to the time-
frequency domain and use magnitude/complex spectrum as the optimizing target. However …

Noise filtering mobile application for speech enhancement using a redundant convolutional encoder-decoder

GA Sampedro, RGC Kim, YJ Aruan… - 2021 1st International …, 2021 - ieeexplore.ieee.org
Hearing aids are the most commonly used devices for hearing impairment. It has been
proven to be effective in helping patients hear better, especially in a quiet and controlled …

Selective kernel network with intermediate supervision loss for monaural speech enhancement

C Chen, Y Lyu, Y Wang, J Li… - 2021 IEEE 21st …, 2021 - ieeexplore.ieee.org
Speech enhancement aims to separate the speech and noise components of noisy speech.
It has greatly benefited from the convolutional encoder-decoder architecture. And designing …