ICASSP 2023

Event-Based Visual Microphone

Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting

VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering

Joint unsupervised and supervised learning for context-aware language identification

Enhanced Low-resolution LiDAR-Camera Calibration Via Depth Interpolation and Supervised Contrastive Learning

SEQUENCE-BASED DEVICE-FREE GESTURE RECOGNITION FRAMEWORK FOR MULTI-CHANNEL ACOUSTIC SIGNALS

Group Personalized Federated Learning

LED: Label Correlation Enhanced Decoder for Multi-Label Text Classification

SELF-SUPERVISED AUDIO-VISUAL SPEECH REPRESENTATIONS LEARNING BY MULTIMODAL SELF-DISTILLATION

Evaluating Speech–Phoneme Alignment and Its Impact on Neural Text-To-Speech Synthesis