Patents by Inventor Ryan Prenger
Ryan Prenger has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11562733Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. Neither a phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.Type: GrantFiled: August 15, 2019Date of Patent: January 24, 2023Assignee: BAIDU USA LLCInventors: Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Gregory Diamos, Erich Eisen, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Adam Coates, Andrew Ng
-
Publication number: 20200394994Abstract: Systems and methods to help synthesize a second audio signal based, at least in part, on one or more neural networks trained using one or more characteristics of a first audio signal. Systems and methods to train one or more neural networks to synthesize a second audio signal based, at least in part, on one or more characteristics of a first audio signal.Type: ApplicationFiled: June 12, 2019Publication date: December 17, 2020Inventors: Ryan Prenger, Rafael Valle, Bryan Catanzaro
-
Patent number: 10540957Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. A phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.Type: GrantFiled: June 9, 2015Date of Patent: January 21, 2020Assignee: BAIDU USA LLCInventors: Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Gregory Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Adam Coates, Andrew Y. Ng
-
Patent number: 10540961Abstract: Described herein are systems and methods for creating and using Convolutional Recurrent Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by the large-scale state-of-the-art speech recognition systems, in embodiments, the strengths of convolutional layers to utilize the structure in the data in time and frequency domains are combined with recurrent layers to utilize context for the entire processed frame. The effect of architecture parameters were examined to determine preferred model embodiments given the performance versus model size tradeoff. Various training strategies are provided to improve performance. In embodiments, using only ˜230 k parameters and yielding acceptably low latency, a CRNN model embodiment demonstrated high accuracy and robust performance in a wide range of environments.Type: GrantFiled: August 28, 2017Date of Patent: January 21, 2020Assignee: Baidu USA LLCInventors: Sercan Arik, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky, Christopher Fougner, Ryan Prenger, Adam Coates
-
Publication number: 20190371298Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. A phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.Type: ApplicationFiled: August 15, 2019Publication date: December 5, 2019Applicant: BAIDU USA LLCInventors: Awni HANNUN, Carl CASE, Jared Casper, Bryan Catanzaro, Gregory Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Adam Coates, Andrew Ng
-
Patent number: 10332509Abstract: Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.Type: GrantFiled: November 21, 2016Date of Patent: June 25, 2019Assignee: Baidu USA, LLCInventors: Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Erich Elsen, Jesse Engel, Christopher Fougner, Xu Han, Awni Hannun, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Dani Yogatama, Chong Wang, Jun Zhan, Zhenyao Zhu, Dario Amodei
-
Patent number: 10319374Abstract: Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.Type: GrantFiled: November 21, 2016Date of Patent: June 11, 2019Assignee: Baidu USA, LLCInventors: Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Erich Elsen, Jesse Engel, Christopher Fougner, Xu Han, Awni Hannun, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Dani Yogatama, Chong Wang, Jun Zhan, Zhenyao Zhu, Dario Amodei
-
Publication number: 20180261213Abstract: Described herein are systems and methods for creating and using Convolutional Recurrent Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by the large-scale state-of-the-art speech recognition systems, in embodiments, the strengths of convolutional layers to utilize the structure in the data in time and frequency domains are combined with recurrent layers to utilize context for the entire processed frame. The effect of architecture parameters were examined to determine preferred model embodiments given the performance versus model size tradeoff. Various training strategies are provided to improve performance. In embodiments, using only ˜230 k parameters and yielding acceptably low latency, a CRNN model embodiment demonstrated high accuracy and robust performance in a wide range of environments.Type: ApplicationFiled: August 28, 2017Publication date: September 13, 2018Applicant: Baidu USA LLCInventors: Sercan Arik, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky, Christopher Fougner, Ryan Prenger, Adam Coates
-
Publication number: 20170148431Abstract: Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.Type: ApplicationFiled: November 21, 2016Publication date: May 25, 2017Applicant: Baidu USA LLCInventors: Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Erich Elsen, Jesse Engel, Christopher Fougner, Xu Han, Awni Hannun, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Dani Yogatama, Chong Wang, Jun Zhan, Zhenyao Zhu, Dario Amodei
-
Publication number: 20170148433Abstract: Embodiments of end-to-end deep learning systems and methods are disclosed to recognize speech of vastly different languages, such as English or Mandarin Chinese. In embodiments, the entire pipelines of hand-engineered components are replaced with neural networks, and the end-to-end learning allows handling a diverse variety of speech including noisy environments, accents, and different languages. Using a trained embodiment and an embodiment of a batch dispatch technique with GPUs in a data center, an end-to-end deep learning system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.Type: ApplicationFiled: November 21, 2016Publication date: May 25, 2017Applicant: Baidu USA LLCInventors: Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Erich Elsen, Jesse Engel, Christopher Fougner, Xu Han, Awni Hannun, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Dani Yogatama, Chong Wang, Jun Zhan, Zhenyao Zhu, Dario Amodei
-
Patent number: 9451883Abstract: Decoding and reconstructing a subjective perceptual or cognitive experience is described. A first set of brain activity data produced in response to a first brain activity stimulus is acquired from a subject using a brain imaging device. An encoding model is used to convert the brain activity data into a corresponding set of predicted response values. A second set of brain activity data produced in response to a second brain activity stimulus is acquired from a subject and decoded using a decoding distribution derived from the encoding model, and the probability the second set of brain activity data corresponds to said predicted response values is determined. The second set of brain activity stimuli is then reconstructed based on the probability of correspondence between the second set of brain activity data and the predicted response values.Type: GrantFiled: December 21, 2012Date of Patent: September 27, 2016Assignee: THE REGENTS OF THE UNIVERSITY OF CALIFORNIAInventors: Jack L. Gallant, Thomas Naselaris, Kendrick Kay, Ryan Prenger
-
Publication number: 20160171974Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. A phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.Type: ApplicationFiled: June 9, 2015Publication date: June 16, 2016Applicant: BAIDU USA LLCInventors: Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Gregory Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubhabrata Sengupta, Adam Coates, Andrew Y. Ng