ICASSP 2022

MULTIMODAL EVALUATION METHOD FOR SOUND EVENT DETECTION

EXPLOITING TEMPORAL CONTEXT IN CNN BASED MULTISOURCE DOA ESTIMATION

CRAMR-RAO BOUND FOR ESTIMATION AFTER MODEL SELECTION AND ITS APPLICATION TO SPARSE VECTOR ESTIMATION

IMPROVING CTC-BASED SPEECH RECOGNITION VIA KNOWLEDGE TRANSFERRING FROM PRE-TRAINED LANGUAGE MODELS

THE DATA/IDENTITY TRADEOFF WITH CENSORED SENSORS

DUAL ATTENTION POOLING NETWORK FOR RECORDING DEVICE CLASSIFICATION USING NEUTRAL AND WHISPERED SPEECH

EFFICIENT IDENTITY-BASED CHAMELEON HASH FOR MOBILE DEVICES

RATE CONTROL FOR LEARNED VIDEO COMPRESSION

ATTENTIVE MAX FEATURE MAP AND JOINT TRAINING FOR ACOUSTIC SCENE CLASSIFICATION

A NOVEL SEQUENTIAL MONTE CARLO FRAMEWORK FOR PREDICTING AMBIGUOUS EMOTION STATES

ASD-TRANSFORMER: EFFICIENT ACTIVE SPEAKER DETECTION USING SELF AND MULTIMODAL TRANSFORMERS

ECO-FEDSPLIT: FEDERATED LEARNING WITH ERROR-COMPENSATED COMPRESSION