← authors · overview

• CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
  2020 · 97 citations
• Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners
  2022 · 11 citations
• The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines
  2018 · 5 citations
• Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition
  2022 · 3 citations
• Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement
  2024 · 3 citations
• Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
  2021 · 2 citations
• Intelligibility prediction with a pretrained noise-robust automatic speech recognition model
  2023 · 1 citations
• Learning task-specific subspaces via interventional post-training of speech foundation models
  2026
• On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
  2020
• Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
  2021
• The Use of Voice Source Features for Sung Speech Recognition
  2021
• Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction
  2022
• On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
  2022