← authors · overview

• A Comparative Study on Transformer vs RNN in Speech Applications
  2019 · 779 citations
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
  2021 · 201 citations
• CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
  2020 · 97 citations
• ESPnet: End-to-End Speech Processing Toolkit
  2018 · 74 citations
• Multi-Modal Data Augmentation for End-to-End ASR
  2018 · 55 citations
• Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition
  2019 · 53 citations
• SUPERB: Speech processing Universal PERformance Benchmark
  2021 · 51 citations
• Multichannel End-to-end Speech Recognition
  2017 · 46 citations
• Neural Speaker Diarization with Speaker-Wise Chain Rule
  2020 · 41 citations
• Recent Developments on ESPnet Toolkit Boosted by Conformer
  2020 · 40 citations
• Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
  2021 · 34 citations
• Towards Online End-to-end Transformer Automatic Speech Recognition
  2019 · 31 citations
• ESPnet2-TTS: Extending the Edge of TTS Research
  2021 · 28 citations
• The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap
  2021 · 27 citations
• Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
  2022 · 24 citations