Large vocabulary continuous speech recognition/search

Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages

ROBUST ACOUSTIC AND SEMANTIC CONTEXTUAL BIASING IN NEURAL TRANSDUCERS FOR SPEECH RECOGNITION

Large-scale Language Model Rescoring on Long-form Data

Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax

Investigation into phone-based subword units for Multilingual end-to-end speech recognition

Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames

CommDRE:Document-level Relation Extraction with Self-supervised Commonsense Learning

CTCBERT: ADVANCING HIDDEN-UNIT BERT WITH CTC OBJECTIVES

TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty

BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder

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