New algorithms and approaches for speech recognition

VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition

Simulating realistic speech overlaps improves multi-talker ASR

Continual Learning for On-Device Speech Recognition using Disentangled Conformers

Multi-output RNN-T Joint Networks for Multi-task Learning of {ASR} and Auxiliary Tasks

Explanations for Automatic Speech Recognition

Improving Scheduled Sampling for Neural Transducer-based ASR

Multi-speaker Data Augmentation for Improved End-to-end Automatic Speech Recognition

STRUCTURED STATE SPACE DECODER FOR SPEECH RECOGNITION AND SYNTHESIS

Implicit vehicle positioning with cooperative lidar sensing

Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis

InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss

ITERATIVE SHALLOW FUSION OF BACKWARD LANGUAGE MODEL FOR END-TO-END SPEECH RECOGNITION