New algorithms and approaches for speech recognition

PRACTICE OF THE CONFORMER ENHANCED AUDIO-VISUAL HUBERT ON MANDARIN AND ENGLISH

I3D: Transformer architectures with input-dependent dynamic depth for speech recognition

Noise-aware target extension with self-distillation for robust speech recognition

A Quantum Approach for Stochastic Constrained Binary Optimization

Factorized AED: Factorized Attention-based Encoder-Decoder for Text-only Domain Adaptive ASR

FINDADAPTNET: FIND AND INSERT ADAPTERS BY LEARNED LAYER IMPORTANCE

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

Group Personalized Federated Learning

token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss

META LEARNING WITH ADAPTIVE LOSS WEIGHT FOR LOW-RESOURCE SPEECH RECOGNITION

Learning Quantum Entanglement Distillation with Noisy Classical Communications