← authors · overview

• On Using SpecAugment for End-to-End Speech Translation
  2019 · 23 citations
• Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
  2020 · 1 citations
• Efficient Sequence Training of Attention Models using Approximative Recombination
  2021
• Automatic Learning of Subword Dependent Model Scales
  2021
• Improving the Training Recipe for a Robust Conformer-based Hybrid Model
  2022
• Mixture Encoder for Joint Speech Separation and Recognition
  2023
• Comparative Analysis of the wav2vec 2.0 Feature Extractor
  2023
• Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
  2023