New algorithms and approaches for speech recognition

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

Adaptive End-pointing with Deep Contextual Multi-armed Bandits

Speaker Change Detection for Transformer Transducer ASR

Accelerating RNN-T Training and Inference Using CTC guidance

DECOUPLED NON-PARAMETRIC KNOWLEDGE DISTILLATION FOR END-TO-END SPEECH TRANSLATION

Domain Adaptation with External Off-Policy Acoustic Catalogs for Scalable Contextual End-To-End Automated Speech Recognition

Speech separation with large-scale self-supervised learning

A Variational Inequality Model for Learning Neural Networks

JEIT: JOINT END-TO-END MODEL AND INTERNAL LANGUAGE MODEL TRAINING FOR SPEECH RECOGNITION

Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion

INTERMEDIATE FINE-TUNING USING IMPERFECT SYNTHETIC SPEECH FOR IMPROVING ELECTROLARYNGEAL SPEECH RECOGNITION

Stabilising and accelerating light gated recurrent units for automatic speech recognition