ICASSP 2020

An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales

Hybrid Active Contour Driven By Double-Weighted Signed Pressure Force For Image Segmentation

Clock Synchronization Over Networks Using Sawtooth Models

Deliberation Model Based Two-Pass End-To-End Speech Recognition

Acu-Net: A 3D Attention Context U-Net For Multiple Sclerosis Lesion Segmentation

Pitchnet: Unsupervised Singing Voice Conversion With Pitch Adversarial Network

Epigraphical Reformulation For Non-Proximable Mixed Norms

A Multi-Phase Gammatone Filterbank For Speech Separation Via Tasnet

A Dynamic Stream Weight Backprop Kalman Filter For Audiovisual Speaker Tracking

Improving Sequence-To-Sequence Speech Recognition Training With On-The-Fly Data Augmentation

Waveffjord: Ffjord-Based Vocoder For Statistical Parametric Speech Synthesis

Passive Intelligent Surface Assisted Mimo Powered Sustainable Iot