ICASSP 2023

Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit

Multi-Label Temporal Evidential Neural Networks for Early Event Detection

Is Quality Enough? Integrating Energy Consumption in a Large-Scale Evaluation of Neural Audio Synthesis Models

Adversarial Guitar Amplifier Modelling With Unpaired Data

On Crowdsourcing-Design with Comparison Category Rating for Evaluating Speech Enhancement algorithms

A Protypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition

Revisit Out-of-vocabulary Problem for Slot Filling: A Unified Contrastive Framework with Multi-level Data Augmentations

TRINET: STABILIZING SELF-SUPERVISED LEARNING FROM COMPLETE OR SLOW COLLAPSE

AN ADAPTER BASED MULTI-LABEL PRE-TRAINING FOR SPEECH SEPARATION AND ENHANCEMENT

Large-scale Language Model Rescoring on Long-form Data

CONTRASTIVE SPEECH MIXUP FOR LOW-RESOURCE KEYWORD SPOTTING

Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering