Jahn Heymann
Amazon (United States)(US)
Publications by Year
Research Areas
Speech and Audio Processing, Speech Recognition and Synthesis, Music and Audio Processing, Advanced Adaptive Filtering Techniques, Natural Language Processing Techniques
Most-Cited Works
- → ESPnet: End-to-End Speech Processing Toolkit(2018)1,306 cited
- → Neural network based spectral mask estimation for acoustic beamforming(2016)494 cited
- → BLSTM supported GEV beamformer front-end for the 3RD CHiME challenge(2015)148 cited
- → Front-end processing for the CHiME-5 dinner party scenario(2018)136 cited
- → Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system(2017)109 cited
- → Far-Field Automatic Speech Recognition(2020)108 cited
- NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing(2018)
- Wide Residual BLSTM Network with Discriminative Speaker Adaptation for Robust Speech Recognition(2016)
- → Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery(2017)46 cited