Robust speech recognition and adaptation

Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection

On the effectiveness of monoaural target source extraction for distant end-to-end automatic speech recognition

Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition

DE’HUBERT: DISENTANGLING NOISE IN A SELF-SUPERVISED MODEL FOR ROBUST SPEECH RECOGNITION

AdapITN: A FAST, RELIABLE, AND DYNAMIC ADAPTIVE INVERSE TEXT NORMALIZATION

Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition

Masked Token Similarity Transfer for Compressing Transformer-Based ASR Models

ROBUST DATA2VEC: NOISE-ROBUST SPEECH REPRESENTATION LEARNING FOR ASR BY COMBINING REGRESSION AND IMPROVED CONTRASTIVE LEARNING

Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting

Data2vec-SG: Improving Self-supervised Learning Representations for Speech Generation Tasks

The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR

SELF-SUPERVISED LEARNING WITH BI-LABEL MASKED SPEECH PREDICTION FOR STREAMING MULTI-TALKER SPEECH RECOGNITION