Audio and speech source separation

Aiding speech harmonic recovery in DNN-based single channel noise reduction using cepstral excitation manipulation (CEM) components

Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning

AUDIO SIGNAL ENHANCEMENT WITH LEARNING FROM POSITIVE AND UNLABELLED DATA

SPEAKERAUGMENT: DATA AUGMENTATION FOR GENERALIZABLE SOURCE SEPARATION VIA SPEAKER PARAMETER MANIPULATION

F0 ESTIMATION FROM TELEPHONE SPEECH USING DEEP FEATURE LOSS

JACAPPELLA CORPUS: A JAPANESE A CAPPELLA VOCAL ENSEMBLE CORPUS

Quantum Graph Transformers

Reverberation as supervision for speech separation

Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation

UX-Net: Filter-and-Process-based Improved U-Net for Real-time Time-domain Audio Separation

ICCRN: INPLACE CEPSTRAL CONVOLUTIONAL RECURRENT NEURAL NETWORK FOR MONAURAL SPEECH ENHANCEMENT

Channel State Information-Free Artificial Noise-Aided Location-Privacy Enhancement