| End-to-end speech recognition using lattice-free MMI H Hadian, H Sameti, D Povey, S Khudanpur Proc. Interspeech, 12-16, 2018 | 210 | 2018 |
| A time-restricted self-attention layer for asr D Povey, H Hadian, P Ghahremani, K Li, S Khudanpur 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 202 | 2018 |
| Investigation of transfer learning for ASR using LF-MMI trained neural networks P Ghahremani, V Manohar, H Hadian, D Povey, S Khudanpur 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017 | 91 | 2017 |
| Semi-supervised training of acoustic models using lattice-free MMI V Manohar, H Hadian, D Povey, S Khudanpur 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 86 | 2018 |
| Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR H Hadian, H Sameti, D Povey, S Khudanpur IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (11 …, 2018 | 49 | 2018 |
| Telephony text-prompted speaker verification using i-vector representation H Zeinali, E Kalantari, H Sameti, H Hadian 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 32 | 2015 |
| Using ASR methods for OCR A Arora, CC Chang, B Rekabdar, B BabaAli, D Povey, D Etter, D Raj, ... 2019 International Conference on Document Analysis and Recognition (ICDAR …, 2019 | 25 | 2019 |
| Improving LF-MMI Using Unconstrained Supervisions for ASR H Hadian, D Povey, H Sameti, J Trmal, S Khudanpur 2018 IEEE Spoken Language Technology Workshop (SLT), 43-47, 2018 | 13 | 2018 |
| Acoustic Modeling from Frequency Domain Representations of Speech. P Ghahremani, H Hadian, H Lv, D Povey, S Khudanpur Interspeech, 1596-1600, 2018 | 13 | 2018 |
| Online signature verification using i-vector representation H Zeinali, B BabaAli, H Hadian IET Biometrics 7 (5), 405-414, 2017 | 12 | 2017 |
| Phone Duration Modeling for LVCSR Using Neural Networks. H Hadian, D Povey, H Sameti, S Khudanpur INTERSPEECH, 518-522, 2017 | 9 | 2017 |
| Towards discriminatively-trained hmm-based end-to-end models for automatic speech recognition H Hadian, H Sameti, D Povey, S Khudanpur Submitted to ICASSP, 2018 | 7 | 2018 |
| Persian large vocabulary name recognition system (FarsName) A Hajitabar, H Sameti, H Hadian, A Safari 2017 Iranian Conference on Electrical Engineering (ICEE), 1580-1583, 2017 | 5 | 2017 |
| Speech activity detection using deep neural networks S Shahsavari, H Sameti, H Hadian 2017 Iranian Conference on Electrical Engineering (ICEE), 1564-1568, 2017 | 4 | 2017 |
| Active learning in noisy conditions for spoken language understanding H Hadian, H Sameti Proceedings of COLING 2014, the 25th International Conference on …, 2014 | 3 | 2014 |
| Continual learning using lattice-free MMI for speech recognition H Hadian, A Gorin arXiv preprint arXiv:2110.07055, 2021 | 2 | 2021 |
| Real-time speaker identification using speaker model distance H Zeinali, H Sameti, H Hadian 2015 23rd Iranian Conference on Electrical Engineering, 643-647, 2015 | 2 | 2015 |
| An alternative to MFCCs for ASR P Ghahramani, H Hadian, D Povey, H Hermansky, S Khudanpur Proc. Interspeech 2020, 1664-1667, 2020 | 1 | 2020 |
| Speech Activity Detection Using Deep Networks S Shahsavari, H Sameti, H Hadian | 1* | |
Daniel PoveyChief Speech Scientist, Xiaomi Corp.Email verificata su xiaomi.com