ICASSP 2023

Beamformer-Guided Target Speaker Extraction

Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis

Less is more: A unified architecture for device-directed speech detection with multiple invocation types

LASSO-BASED FAST RESIDUAL RECOVERY FOR MODULO SAMPLING

Ensemble prosody prediction for expressive speech synthesis

Massively Multilingual Shallow Fusion with Large Language Models

Identifying Coordination in a Cognitive Radar Network - A Multi-Objective Inverse Reinforcement Learning Approach

Dual-based Online Learning of Dynamic Network Topologies

Pyramid Dynamic Inference: Encouraging Faster Inference via Early Exit Boosting

Improving Automatic Sleep Staging via Temporal Smoothness Regularization

Spatially Selective Deep Non-linear Filters for Speaker Extraction

Egocentric Audio-Visual Noise Suppression