Kazuki Irie
Harvard University(US)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Speech Recognition and Synthesis, Neural Networks and Applications, Domain Adaptation and Few-Shot Learning
Most-Cited Works
- → Improved Training of End-to-end Attention Models for Speech Recognition(2018)280 cited
- → A Comparison of Transformer and LSTM Encoder Decoder Models for ASR(2019)222 cited
- → Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling(2019)183 cited
- → Language Modeling with Deep Transformers(2019)177 cited
- → LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition(2016)101 cited
- → The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers(2021)54 cited
- → The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment(2020)47 cited
- → On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition(2019)40 cited
- → Training Language Models for Long-Span Cross-Sentence Evaluation(2019)37 cited
- → The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation(2016)32 cited