-
QUT-NOISE-TIMIT
The QUT-NOISE-TIMIT dataset is a dataset for speech enhancement. It consists of clean speech and noise. -
Database of Multichannel In-Ear and Behind-the-Ear Head-Related and Binaural ...
The dataset used for training and validation of the proposed deep binaural MFMVDR filter, comprising simulated binaural room impulse responses and clean speech and noise. -
INTERSPEECH 2020 Deep Noise Suppression Challenge
The dataset used for evaluation of the proposed deep binaural MFMVDR filter, comprising measured binaural room impulse responses and clean speech and noise. -
Clarity-2021 Challenges: Machine Learning Challenges for Advancing Hearing Ai...
The dataset used for training and validation of the proposed deep binaural MFMVDR filter, comprising simulated binaural room impulse responses and clean speech and noise. -
SELF-SUPERVISED SPEECH QUALITY ESTIMATION AND ENHANCEMENT USING ONLY CLEAN SP...
The proposed self-supervised speech quality estimator trained only on clean speech. -
Using power level difference for near field dual-microphone speech enhancement
Using power level difference for near field dual-microphone speech enhancement -
Interspeech 2021 AEC Challenge
The dataset used for testing the proposed complex-valued neural network architecture for joint acoustic echo cancellation and noise suppression. -
Microsoft AEC Challenges
The dataset used for training and testing the proposed complex-valued neural network architecture for joint acoustic echo cancellation and noise suppression.
