Acoustic modeling for automatic speech recognition

Lattice-free Sequence Discriminative Training for Phoneme-based Neural Transducers

DELAY-PENALIZED TRANSDUCER FOR LOW-LATENCY STREAMING ASR

Self-Convolution for Automatic Speech Recognition

AN ADAPTER BASED MULTI-LABEL PRE-TRAINING FOR SPEECH SEPARATION AND ENHANCEMENT

Dialog act guided contextual adapter for personalized speech recognition

LMCodec: A Low Bitrate Speech Codec With Causal Transformer Models

AN ISOTROPY ANALYSIS FOR SELF-SUPERVISED ACOUSTIC UNIT EMBEDDINGS ON THE ZERO RESOURCE SPEECH CHALLENGE 2021 FRAMEWORK

Federated Self-Learning with Weak Supervision for Speech Recognition

PREDICTING MULTI-CODEBOOK VECTOR QUANTIZATION INDEXES FOR KNOWLEDGE DISTILLATION

Modular Conformer Training for Flexible End-to-End ASR

IMPROVING NON-AUTOREGRESSIVE SPEECH RECOGNITION WITH AUTOREGRESSIVE PRETRAINING

Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy