automatic speech recognition

INTEGRATING TEXT INPUTS FOR TRAINING AND ADAPTING RNN TRANSDUCER ASR MODELS

ASR-AWARE END-TO-END NEURAL DIARIZATION

IMPROVED META LEARNING FOR LOW RESOURCE SPEECH RECOGNITION

IMPROVED SIMULATION OF REALISTICALLY-SPATIALISED SIMULTANEOUS SPEECH USING MULTI-CAMERA ANALYSIS IN THE CHIME-5 DATASET

TINYS2I: A SMALL-FOOTPRINT UTTERANCE CLASSIFICATION MODEL WITH CONTEXTUAL SUPPORT FOR ON-DEVICE SLU

IMPROVING SELF-SUPERVISED LEARNING FOR SPEECH RECOGNITION WITH INTERMEDIATE LAYER SUPERVISION

OPTIMIZE WAV2VEC2S ARCHITECTURE FOR SMALL TRAINING SET THROUGH ANALYZING ITS PRE-TRAINED MODELS ATTENTION PATTERN

EFFICIENT ADAPTER TRANSFER OF SELF-SUPERVISED SPEECH MODELS FOR AUTOMATIC SPEECH RECOGNITION

SELF-CRITICAL SEQUENCE TRAINING FOR AUTOMATIC SPEECH RECOGNITION

Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition

FUSING ASR OUTPUTS IN JOINT TRAINING FOR SPEECH EMOTION RECOGNITION

PERSONALIZED AUTOMATIC SPEECH RECOGNITION TRAINED ON SMALL DISORDERED SPEECH DATASETS