| Accepting voice commands based on user identity SI Blanksteen, B Hoffmeister US Patent 9,098,467, 2015 | 365 | 2015 |
| Anchored speech detection and speech recognition SHK Parthasarathi, B Hoffmeister, B King, R Maas US Patent 10,373,612, 2019 | 279 | 2019 |
| Keyword detection modeling using contextual and environmental information R Prasad, KJ Basye, S Matsoukas, R Ramachandran, SNP Vitaladevuni, ... US Patent 9,697,828, 2017 | 236 | 2017 |
| Speech model retrieval in distributed speech recognition systems B Hoffmeister, HE Secker-Walker, JC O'neill US Patent 9,190,057, 2015 | 205 | 2015 |
| Multi-task learning and weighted cross-entropy for DNN-based keyword spotting S Panchapagesan, M Sun, A Khare, S Matsoukas, A Mandal, ... | 166 | 2016 |
| Language model speech endpointing B Hoffmeister, A Rastrow, B Liu US Patent 10,121,471, 2018 | 154 | 2018 |
| Speech processing for digital home assistants: Combining signal processing with deep-learning techniques R Haeb-Umbach, S Watanabe, T Nakatani, M Bacchiani, B Hoffmeister, ... IEEE Signal processing magazine 36 (6), 111-124, 2019 | 151 | 2019 |
| The RWTH Aachen University open source speech recognition system D Rybach, C Gollan, G Heigold, B Hoffmeister, J Lööf, R Schlüter, H Ney Tenth Annual Conference of the International Speech Communication Association, 2009 | 145 | 2009 |
| Speech recognizer with multi-directional decoding MME Bisani, N Strom, B Hoffmeister, RP Thomas US Patent 9,286,897, 2016 | 112 | 2016 |
| Keyword spotting with competitor models B Hoffmeister US Patent 9,159,319, 2015 | 101 | 2015 |
| Low latency and memory efficient keywork spotting B Hoffmeister US Patent 9,390,708, 2016 | 90 | 2016 |
| Monophone-based background modeling for two-stage on-device wake word detection M Wu, S Panchapagesan, M Sun, J Gu, R Thomas, SNP Vitaladevuni, ... 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 83 | 2018 |
| Error tolerant neural network model compression B Liu, MR Bastian, B Hoffmeister, S Panchapagesan, A Rastrow US Patent 10,229,356, 2019 | 80 | 2019 |
| Just ASK: building an architecture for extensible self-service spoken language understanding A Kumar, A Gupta, J Chan, S Tucker, B Hoffmeister, M Dreyer, ... arXiv preprint arXiv:1711.00549, 2017 | 77 | 2017 |
| The RWTH 2007 TC-STAR evaluation system for european English and Spanish. J Lööf, C Gollan, S Hahn, G Heigold, B Hoffmeister, C Plahl, D Rybach, ... Interspeech, 2145-2148, 2007 | 77 | 2007 |
| Lattice encoding using recurrent neural networks F Ladhak, A Gandhe, M Dreyer, A Rastrow, B Hoffmeister, L Mathias US Patent 10,176,802, 2019 | 76 | 2019 |
| Frame based system combination and a comparison with weighted ROVER and CNC B Hoffmeister, T Klein, R Schlüter, H Ney Ninth International Conference on Spoken Language Processing, 2006 | 76 | 2006 |
| LATTICE RNN: Recurrent neural networks over lattices F Ladhak, A Gandhe, M Dreyer, L Mathias, A Rastrow, B Hoffmeister | 69 | 2016 |
| Using adaptation data with cloud-based speech recognition H Secker-Walker, B Hoffmeister, R Thomas, S Salvador, K Ramakrishnan US Patent 8,996,372, 2015 | 67 | 2015 |
| Local speech recognition of frequent utterances B Hoffmeister, J O'neill US Patent 9,070,367, 2015 | 66 | 2015 |
Roland MaasSr. Science Manager at AmazonVerified email at amazon.com
