ICASSP 2023

Two-Phase Prototypical Contrastive Domain Generalization for Cross-Subject EEG-Based Emotion Recognition

A Reality Check and A Practical Baseline for Semantic Speech Embedding

DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks

StreamSpeech: Low-Latency Neural Architecture for High-Quality On-Device Speech Synthesis

Cross-Modal Mutual Learning for Cued Speech Recognition

Building Change Detection using Cross-temporal Feature Interaction Network

Calibrating AI Models for Few-Shot Demodulation via Conformal Prediction

LiteG2P: A fast, light and high accuracy model for Grapheme-to-Phoneme conversion

Phonetic RNN-Transducer for Mispronunciation Diagnosis

ST-MVDNet++: Improve Vehicle Detection with Lidar-Radar Geometrical Augmentation via Self-Training

SELF-HEALING THROUGH ERROR DETECTION, ATTRIBUTION, AND RETRAINING

Question Answering system with Sparse and Noisy Feedback