← authors · overview

• Language Modeling with Deep Transformers
  2019 · 177 citations
• On Using SpecAugment for End-to-End Speech Translation
  2019 · 23 citations
• Efficient Training of Neural Transducer for Speech Recognition
  2022 · 13 citations
• Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Model
  2020 · 11 citations
• Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
  2021 · 10 citations
• Context-Dependent Acoustic Modeling without Explicit Phone Clustering
  2020 · 9 citations
• Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
  2019 · 7 citations
• A study of latent monotonic attention variants
  2021 · 7 citations
• Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Bias
  2020 · 6 citations
• A comprehensive study of batch construction strategies for recurrent neural networks in MXNet
  2017 · 5 citations
• A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
  2020 · 5 citations
• Towards Consistent Hybrid HMM Acoustic Modeling
  2021 · 4 citations
• Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
  2021 · 4 citations
• On Language Model Integration for RNN Transducer based Speech Recognition
  2021 · 4 citations
• Is Encoder-Decoder Redundant for Neural Machine Translation?
  2022 · 3 citations