Robust speech recognition and adaptation

Rate Region Characterization for Semantics and Bits Based Multiuser Communications

AN ANALYSIS OF DEGENERATING SPEECH DUE TO PROGRESSIVE DYSARTHRIA ON ASR PERFORMANCE

Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models

CB-Conformer: Contextual Biasing Conformer for Biased Word Recognition

HuBERT-AGG: Aggregated Representation Distillation of Hidden-unit BERT for Robust Speech Recognition

Adapting a self-supervised speech representation for noisy speech emotion recognition by using contrastive teacher-student learning

Self-Supervised Learning-Based Source Separation for Meeting Data

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR

Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation