Issued Patents All Time
Showing 1–25 of 42 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12217768 | Audio-visual separation of on-screen sounds based on machine learning models | Efthymios Tzinis, Scott Wisdom, Aren Jansen | 2025-02-04 |
| 11756570 | Audio-visual separation of on-screen sounds based on machine learning models | Efthymios Tzinis, Scott Wisdom, Aren Jansen | 2023-09-12 |
| 11133011 | System and method for multichannel end-to-end speech recognition | Shinji Watanabe, Tsubasa OCHIAI, Takaaki Hori | 2021-09-28 |
| 11086918 | Method and system for multi-label classification | Takaaki Hori, Chiori Hori, Shinji Watanabe, Bret Harsham, Jonathan Le Roux | 2021-08-10 |
| 10811000 | Methods and systems for recognizing simultaneous speech by multiple speakers | Jonathan Le Roux, Takaaki Hori, Shane Settle, Hiroshi Seki, Shinji Watanabe | 2020-10-20 |
| 10726856 | Methods and systems for enhancing audio signals corrupted by noise | Jonathan Le Roux, Shinji Watanabe, Gordon Wichern | 2020-07-28 |
| 10672388 | Method and apparatus for open-vocabulary end-to-end speech recognition | Takaaki Hori, Shinji Watanabe | 2020-06-02 |
| 10593321 | Method and apparatus for multi-lingual end-to-end speech recognition | Shinji Watanabe, Takaaki Hori, Hiroshi Seki, Jonathan Le Roux | 2020-03-17 |
| 10592800 | Neural networks for transforming signals | Jonathan Le Roux, Felix Weninger | 2020-03-17 |
| 10529349 | Methods and systems for end-to-end speech separation with unfolded iterative phase reconstruction | Jonathan Le Roux, Zhongqiu Wang, Gordon Wichern | 2020-01-07 |
| 10417498 | Method and system for multi-modal fusion model | Chiori Hori, Takaaki Hori, Tim Marks | 2019-09-17 |
| 10176799 | Method and system for training language models to reduce recognition errors | Takaaki Hori, Chiori Hori, Shinji Watanabe | 2019-01-08 |
| 9881631 | Method for enhancing audio signal using phase information | Hakan Erdogan, Shinji Watanabe, Jonathan Le Roux | 2018-01-30 |
| 9842106 | Method and system for role dependent context sensitive spoken and textual language understanding with neural networks | Chiori Hori, Takaaki Hori, Shinji Watanabe | 2017-12-12 |
| 9837075 | Statistical voice dialog system and method | Shinji Watanabe | 2017-12-05 |
| 9685155 | Method for distinguishing components of signal of environment | Jonathan Le Roux, Shinji Watanabe, Zhuo Chen | 2017-06-20 |
| 9679559 | Source signal separation by discriminatively-trained non-negative matrix factorization | Jonathan Le Roux, Felix Weninger, Shinji Watanabe | 2017-06-13 |
| 9661414 | Flat-panel acoustic apparatus | Jonathan Le Roux, William S. Yerazunis, Petros Boufounos, Laurent Daudet | 2017-05-23 |
| 9601130 | Method for processing speech signals using an ensemble of speech enhancement procedures | Jonathan Le Roux, Shinji Watanabe | 2017-03-21 |
| 9582753 | Neural networks for transforming signals | Jonathan Le Roux, Felix Weninger | 2017-02-28 |
| 9477895 | Method and system for detecting events in an acoustic signal subject to cyclo-stationary noise | Vamsi Krishna POTLURU, Jonathan Le Roux | 2016-10-25 |
| 9434389 | Actions prediction for hypothetical driving conditions | Bret Harsham, Jonathan Le Roux, Daniel Nikolaev Nikovski, Alan W. Esenther | 2016-09-06 |
| 9368110 | Method for distinguishing components of an acoustic signal | Jonathan Le Roux, Shinji Watanabe, Zhuo Chen | 2016-06-14 |
| 9324338 | Denoising noisy speech signals using probabilistic model | Jonathan Le Roux, Umut Simsekli | 2016-04-26 |
| 9305306 | Method and system for autonomously delivering information to drivers | Daniel Nikolaev Nikovski, Bret Harsham, Dirk Brinkman | 2016-04-05 |