ICASSP 2023

WavSyncSwap: End-to-End Portrait-Customized Audio-Driven Talking Face Generation

Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech

FINE-GRAINED PRIVATE KNOWLEDGE DISTILLATION

Two-stage UNet with multi-axis gated multilayer perceptron for monaural noisy-reverberant speech enhancement

Frequency and Scale Perspectives of Feature Extraction

Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition

Once-for-All Sequence Compression for Self-Supervised Speech Models

Receptive Field Reliant Zero-Cost Proxies for Neural Architecture Search

SMCL: SALIENCY MASKED CONTRASTIVE LEARNING FOR LONG-TAILED VISUAL RECOGNITION

RIS REFLECTION AND PLACEMENT OPTIMISATION FOR UNDERLAY D2D COMMUNICATIONS IN COGNITIVE CELLULAR NETWORKS

Autonomous Navigation of a Robotic Swarm in Space Exploration Missions

Prosody-controllable spontaneous TTS with neural HMMs