| Musiclm: Generating music from text A Agostinelli, TI Denk, Z Borsos, J Engel, M Verzetti, A Caillon, Q Huang, ... arXiv preprint arXiv:2301.11325, 2023 | 440 | 2023 |
| Hotword recognition M Sharifi, JN Foerster US Patent 9,747,926, 2017 | 425 | 2017 |
| Audiolm: a language modeling approach to audio generation Z Borsos, R Marinier, D Vincent, E Kharitonov, O Pietquin, M Sharifi, ... IEEE/ACM transactions on audio, speech, and language processing 31, 2523-2533, 2023 | 415 | 2023 |
| Hotword detection on multiple devices M Sharifi US Patent 9,318,107, 2016 | 398 | 2016 |
| Device leadership negotiation among voice interface devices K Mixter, DM Casado, AH Gruenstein, T Tai, CT Hughes, MN Sharifi US Patent 9,812,128, 2017 | 382 | 2017 |
| Systems and methods for live media content matching M Sharifi US Patent 9,661,361, 2017 | 324 | 2017 |
| Fr\'echet audio distance: A metric for evaluating music enhancement algorithms K Kilgour, M Zuluaga, D Roblek, M Sharifi arXiv preprint arXiv:1812.08466, 2018 | 291 | 2018 |
| Hotword detection on multiple devices M Sharifi US Patent 9,514,752, 2016 | 268 | 2016 |
| Hotword recognition M Sharifi, JN Foerster US Patent 9,928,840, 2018 | 264 | 2018 |
| Hotword detection on multiple devices M Sharifi US Patent 10,134,398, 2018 | 247 | 2018 |
| Promoting voice actions to hotwords M Sharifi US Patent 9,263,035, 2016 | 244 | 2016 |
| Promoting voice actions to hotwords M Sharifi US Patent 8,719,039, 2014 | 224 | 2014 |
| Answering questions using environmental context M Sharifi, G Postelnicu US Patent App. 13/626,439, 2014 | 203 | 2014 |
| Recorded media hotword trigger suppression AH Gruenstein, J Schalkwyk, M Sharifi US Patent 10,867,600, 2020 | 195 | 2020 |
| Efficient utterance-specific endpointer triggering for always-on hotwording M Sharifi, D Roblek, S Siddhartha US Patent 8,775,191, 2014 | 168 | 2014 |
| Speak, read and prompt: High-fidelity text-to-speech with minimal supervision E Kharitonov, D Vincent, Z Borsos, R Marinier, S Girgin, O Pietquin, ... Transactions of the Association for Computational Linguistics 11, 1703-1718, 2023 | 134 | 2023 |
| Providing pre-computed hotword models M Sharifi US Patent 9,263,042, 2016 | 127 | 2016 |
| Speaker identification using a text-independent model and a text-dependent model M Sharifi, D Roblek US Patent 10,255,922, 2019 | 116 | 2019 |
| Audiopalm: A large language model that can speak and listen PK Rubenstein, C Asawaroengchai, DD Nguyen, A Bapna, Z Borsos, ... arXiv preprint arXiv:2306.12925, 2023 | 113 | 2023 |
| Simulated hyperlinks on a mobile device based on user intent and a centered selection of text M Sharifi, D Petrou US Patent 10,055,390, 2018 | 95 | 2018 |
Dominik RoblekSenior Staff Software Engineer, Google ResearchPatvirtintas el. paštas google.com
