| Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech S Jain, V Vo, S Mahto, A LeBel, JS Turek, A Huth Advances in Neural Information Processing Systems 33, 13738-13749, 2020 | 30 | 2020 |
| Multi-timescale representation learning in LSTM Language Models S Mahto, VA Vo, JS Turek, AG Huth arXiv preprint arXiv:2009.12727, 2020 | 28 | 2020 |
| Ear acoustic biometrics using inaudible signals and its application to continuous user authentication S Mahto, T Arakawa, T Koshinak 2018 26th European Signal Processing Conference (EUSIPCO), 1407-1411, 2018 | 26 | 2018 |
| i-Vector Transformation Using a Novel Discriminative Denoising Autoencoder for Noise-Robust Speaker Recognition. S Mahto, H Yamamoto, T Koshinaka Interspeech, 3722-3726, 2017 | 16 | 2017 |
| Pattern recognition apparatus, pattern recognition method, and computer-readable recording medium S Mahto US Patent App. 17/044,399, 2021 | 6 | 2021 |
| Pattern recognition apparatus, method and medium S Mahto, H Yamamoto, T Koshinaka US Patent App. 16/344,096, 2019 | 1 | 2019 |
| Recognition apparatus, recognition method, and computer-readable recording medium S Mahto, T Arakawa US Patent App. 17/289,536, 2021 | | 2021 |
Alexander HuthAssistant Professor CS & Neuroscience UT AustinBestätigte E-Mail-Adresse bei cs.utexas.edu
