Large vocabulary continuous speech recognition/search

Lego-Features: Exporting modular encoder features for streaming and deliberation ASR

CUMULATIVE ATTENTION BASED STREAMING TRANSFORMER ASR WITH INTERNAL LANGUAGE MODEL JOINT TRAINING AND RESCORING

IMPROVEMENTS TO EMBEDDING-MATCHING ACOUSTIC-TO-WORD ASR USING MULTIPLE-HYPOTHESIS PRONUNCIATION-BASED EMBEDDINGS

Improving CTC-based ASR Models with Gated Interlayer Collaboration

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

Variable Attention Masking for Configurable Transformer Transducer Speech Recognition

ROBUST HYPOTHESIS TESTING WITH MOMENT CONSTRAINED UNCERTAINTY SETS

Cross-Training: A Semi-Supervised Training Scheme for Speech Recognition

Multi-View Millimeter-Wave Imaging Over Wireless Cellular Network

RELIABLE BEAMFORMING AT TERAHERTZ BANDS: ARE CAUSAL REPRESENTATIONS THE WAY FORWARD?

Reducing the gap between streaming and non-streaming Transducer-based ASR models by adaptive two-stage knowledge distillation