ICASSP 2022

CALL-SIGN RECOGNITION AND UNDERSTANDING FOR NOISY AIR-TRAFFIC TRANSCRIPTS USING SURVEILLANCE INFORMATION

DISTRIBUTION AUGMENTATION FOR LOW-RESOURCE EXPRESSIVE TEXT-TO-SPEECH

IMPROVING BIOMEDICAL NAMED ENTITY RECOGNITION WITH A UNIFIED MULTI-TASK MRC FRAMEWORK

PRIVACY-PRESERVING FEDERATED MULTI-TASK LINEAR REGRESSION: A ONE-SHOT LINEAR MIXING APPROACH INSPIRED BY GRAPH REGULARIZATION

KNOWLEDGE DISTILLATION FROM LANGUAGE MODEL TO ACOUSTIC MODEL: A HIERARCHICAL MULTI-TASK LEARNING APPROACH

Ada-JSR: SAMPLE EFFICIENT ADAPTIVE JOINT SUPPORT RECOVERY FROM EXTREMELY COMPRESSED MEASUREMENT VECTORS

MIXED IN TIME AND MODALITY: CURSE OR BLESSING? CROSS-INSTANCE DATA AUGMENTATION FOR WEAKLY SUPERVISED MULTIMODAL TEMPORAL FUSION

MAXIMIZING AUDIO EVENT DETECTION MODEL PERFORMANCE ON SMALL DATASETS THROUGH KNOWLEDGE TRANSFER, DATA AUGMENTATION, AND PRETRAINING: AN ABLATION STUDY

KNOWLEDGE TRANSFER FROM LARGE-SCALE PRETRAINED LANGUAGE MODELS TO END-TO-END SPEECH RECOGNIZERS

IMPORTANTAUG: A DATA AUGMENTATION AGENT FOR SPEECH

LPC AUGMENT: AN LPC-BASED ASR DATA AUGMENTATION ALGORITHM FOR LOW AND ZERO-RESOURCE CHILDREN?S DIALECTS

AUGMENTATION STRATEGY OPTIMIZATION FOR LANGUAGE UNDERSTANDING