Acoustic modeling for automatic speech recognition

More Speaking or More Speakers?

SELF-SUPERVISED ACCENT LEARNING FOR UNDER-RESOURCED ACCENTS USING NATIVE LANGUAGE DATA

Context-aware Fine-tuning of Self-supervised speech models

A Reality Check and A Practical Baseline for Semantic Speech Embedding

Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models

EFFECTIVE TRAINING OF RNN TRANSDUCER MODELS ON DIVERSE SOURCES OF SPEECH AND TEXT DATA

DIAGONAL STATE SPACE AUGMENTED TRANSFORMERS FOR SPEECH RECOGNITION

HEALTHCALL CORPUS AND TRANSFORMER EMBEDDINGS FROM HEALTHCARE CUSTOMER-AGENT CONVERSATIONS

Anchored Speech Recognition with Neural Transducers

Robust Audio-Visual ASR with Unified Cross-modal Attention

Unsupervised model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition

UFO2: A unified pre-training framework for online and offline speech recognition