Patents by Inventor Mohammad SHOEYBI
Mohammad SHOEYBI 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).
-
Publication number: 20240095460Abstract: In various examples, systems and methods that use dialogue systems associated with various machine systems and applications are described. For instance, the systems and methods may receive text data representing speech, such as a question associated with a vehicle or other machine type. The systems and methods then use a retrieval system(s) to retrieve a question/answer pair(s) associated with the text data and/or contextual information associated with the text data. In some examples, the contextual information is associated with a knowledge base associated with or corresponding to the vehicle. The systems and methods then generate a prompt using the text data, the question/answer pair(s), and/or the contextual information. Additionally, the systems and methods determine, using a language model(s) and based at least on the prompt, an output associated with the text data. For instance, the output may include information that answers the question associated with the vehicle.Type: ApplicationFiled: September 19, 2022Publication date: March 21, 2024Inventors: Peng Xu, Mostofa Patwary, Rajath Shetty, Niral Lalit Pathak, Ratin Kumar, Bryan Catanzaro, Mohammad Shoeybi
-
Publication number: 20240095447Abstract: Apparatuses, systems, and techniques are presented to identify and prevent generation of restricted content. In at least one embodiment, one or more neural networks are used to identify restricted content based only on the restricted content.Type: ApplicationFiled: June 22, 2022Publication date: March 21, 2024Inventors: Wei Ping, Boxin Wang, Chaowei Xiao, Mohammad Shoeybi, Mostofa Patwary, Anima Anandkumar, Bryan Catanzaro
-
Patent number: 11705107Abstract: Embodiments of a production-quality text-to-speech (TTS) system constructed from deep neural networks are described. System embodiments comprise five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For embodiments of the segmentation model, phoneme boundary detection was performed with deep neural networks using Connectionist Temporal Classification (CTC) loss. For embodiments of the audio synthesis model, a variant of WaveNet was created that requires fewer parameters and trains faster than the original. By using a neural network for each component, system embodiments are simpler and more flexible than traditional TTS systems, where each component requires laborious feature engineering and extensive domain expertise. Inference with system embodiments may be performed faster than real time.Type: GrantFiled: October 1, 2020Date of Patent: July 18, 2023Assignee: Baidu USA LLCInventors: Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, John Miller, Andrew Ng, Jonathan Raiman, Shubhahrata Sengupta, Mohammad Shoeybi
-
Patent number: 11556775Abstract: Described herein are systems and methods for compressing and speeding up dense matrix multiplications as found, for examples, in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, trace norm regularization technique embodiments were introduced and studied for training low rank factored versions of matrix multiplications. Compared to standard low rank training, the methods more consistently lead to good accuracy versus number of parameter trade-offs and can be used to speed-up training of large models. Faster inference may be further enabled on ARM processors through kernels optimized for small batch sizes, resulting in speed ups over the currently used library. Beyond LVCSR, the techniques are also generally applicable to embedded neural networks with large fully connected or recurrent layers.Type: GrantFiled: October 3, 2018Date of Patent: January 17, 2023Assignee: Baidu USA LLCInventors: Markus Kliegl, Siddharth Goyal, Kexin Zhao, Kavya Srinet, Mohammad Shoeybi
-
Publication number: 20210067735Abstract: Apparatuses, systems, and techniques to enhance video. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having a higher frame rate, higher resolution, or reduced number of missing or corrupt video frames.Type: ApplicationFiled: September 3, 2019Publication date: March 4, 2021Inventors: Fitsum Reda, Deqing Sun, Aysegul Dundar, Mohammad Shoeybi, Guilin Liu, Kevin Shih, Andrew Tao, Jan Kautz, Bryan Catanzaro
-
Publication number: 20210027762Abstract: Embodiments of a production-quality text-to-speech (TTS) system constructed from deep neural networks are described. System embodiments comprise five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For embodiments of the segmentation model, phoneme boundary detection was performed with deep neural networks using Connectionist Temporal Classification (CTC) loss. For embodiments of the audio synthesis model, a variant of WaveNet was created that requires fewer parameters and trains faster than the original. By using a neural network for each component, system embodiments are simpler and more flexible than traditional TTS systems, where each component requires laborious feature engineering and extensive domain expertise. Inference with system embodiments may be performed faster than real time.Type: ApplicationFiled: October 1, 2020Publication date: January 28, 2021Applicant: Baidu USA LLCInventors: Sercan O. ARIK, Mike CHRZANOWSKI, Adam COATES, Gregory DIAMOS, Andrew GIBIANSKY, John MILLER, Andrew NG, Jonathan RAIMAN, Shubhahrata SENGUPTA, Mohammad SHOEYBI
-
Patent number: 10872598Abstract: Embodiments of a production-quality text-to-speech (TTS) system constructed from deep neural networks are described. System embodiments comprise five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For embodiments of the segmentation model, phoneme boundary detection was performed with deep neural networks using Connectionist Temporal Classification (CTC) loss. For embodiments of the audio synthesis model, a variant of WaveNet was created that requires fewer parameters and trains faster than the original. By using a neural network for each component, system embodiments are simpler and more flexible than traditional TTS systems, where each component requires laborious feature engineering and extensive domain expertise. Inference with system embodiments may be performed faster than real time.Type: GrantFiled: January 29, 2018Date of Patent: December 22, 2020Assignee: Baidu USA LLCInventors: Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, John Miller, Andrew Ng, Jonathan Raiman, Shubhahrata Sengupta, Mohammad Shoeybi
-
Publication number: 20190122108Abstract: Described herein are systems and methods for compressing and speeding up dense matrix multiplications as found, for examples, in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, trace norm regularization technique embodiments were introduced and studied for training low rank factored versions of matrix multiplications. Compared to standard low rank training, the methods more consistently lead to good accuracy versus number of parameter trade-offs and can be used to speed-up training of large models. Faster inference may be further enabled on ARM processors through kernels optimized for small batch sizes, resulting in speed ups over the currently used library. Beyond LVCSR, the techniques are also generally applicable to embedded neural networks with large fully connected or recurrent layers.Type: ApplicationFiled: October 3, 2018Publication date: April 25, 2019Applicant: Baidu USA LLCInventors: Markus KLIEGL, Siddharth GOYAL, Kexin ZHAO, Kavya SRINET, Mohammad SHOEYBI
-
Publication number: 20180247636Abstract: Embodiments of a production-quality text-to-speech (TTS) system constructed from deep neural networks are described. System embodiments comprise five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For embodiments of the segmentation model, phoneme boundary detection was performed with deep neural networks using Connectionist Temporal Classification (CTC) loss. For embodiments of the audio synthesis model, a variant of WaveNet was created that requires fewer parameters and trains faster than the original. By using a neural network for each component, system embodiments are simpler and more flexible than traditional TTS systems, where each component requires laborious feature engineering and extensive domain expertise. Inference with system embodiments may be performed faster than real time.Type: ApplicationFiled: January 29, 2018Publication date: August 30, 2018Applicant: Baidu USA LLCInventors: Sercan O. ARIK, Mike CHRZANOWSKI, Adam COATES, Gregory DIAMOS, Andrew GIBIANSKY, John MILLER, Andrew NG, Jonathan RAIMAN, Shubhahrata SENGUPTA, Mohammad SHOEYBI