← authors · overview

• Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models
  2021 · 13 citations
• RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
  2020 · 12 citations
• Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
  2021 · 10 citations
• Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models
  2019 · 3 citations
• Residual Energy-Based Models for End-to-End Speech Recognition
  2021 · 3 citations
• Learning Word-Level Confidence For Subword End-to-End ASR
  2021 · 2 citations
• Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
  2021 · 2 citations
• Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models
  2021 · 2 citations
• Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data
  2020 · 1 citations
• Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition
  2021 · 1 citations
• Instruction-Following Speech Recognition
  2023