Inventor · disambiguated record
Bryan Catanzaro
Also filed as: CATANZARO BRYAN · CATANZARO BRYAN CHRISTOPHER
18 granted patents·28 pending applications·163 citations·filing 2010–2025
93Inventor score
Top patents by PatentIndex Score
46 records- 0196US10332509B2End-to-end speech recognitionBAIDU USA LLC·Filed 2016·Granted Jun 25, 2019·77 cites·20 claims
- 0294US11810268B2Image enhancement using one or more neural networksNVIDIA CORP·Filed 2022·Granted Nov 7, 2023·5 cites·40 claims
- 0393US10319374B2Deployed end-to-end speech recognitionBAIDU USA LLC·Filed 2016·Granted Jun 11, 2019·24 cites·20 claims
- 0491US12400291B2Image enhancement using one or more neural networksNVIDIA CORP·Filed 2021·Granted Aug 26, 2025·2 cites·17 claims
- 0590US10540957B2Systems and methods for speech transcriptionBAIDU USA LLC·Filed 2015·Granted Jan 21, 2020·14 cites·20 claims
- 0689US10223333B2Performing multi-convolution operations in a parallel processing systemNVIDIA CORP·Filed 2015·Granted Mar 5, 2019·25 cites·18 claims
- 0787US12488778B2Normalizing flows with neural splines for high-quality speech synthesisNVIDIA CORP·Filed 2023·Granted Dec 2, 2025·2 cites·19 claims
- 0882US10769533B2Systems and methods for efficient neural network deploymentsBAIDU USA LLC·Filed 2016·Granted Sep 8, 2020·4 cites·20 claims
- 0980US11902705B2Video prediction using one or more neural networksNVIDIA CORP·Filed 2019·Granted Feb 13, 2024·4 cites·37 claims
- 1077US10832120B2Systems and methods for a multi-core optimized recurrent neural networkBAIDU USA LLC·Filed 2016·Granted Nov 10, 2020·4 cites·20 claims
- 1172US11562733B2Deep learning models for speech recognitionBAIDU USA LLC·Filed 2019·Granted Jan 24, 2023·2 cites·20 claims
- 1269US2025384295A1Techniques for implementing multimodal large language models with mixtures of vision encodersNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1369US2025384268A1Techniques for implementing multimodal large language models with mixtures of vision encodersNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1468US2023419947A1Unsupervised alignment for text to speech synthesis using neural networksNVIDIA CORP·Filed 2023·Application pending·0 cites
- 1568US2023402028A1Unsupervised alignment for text to speech synthesis using neural networksNVIDIA CORP·Filed 2023·Application pending·0 cites
- 1666US2023186428A1Techniques to use a neural network to expand an imageNVIDIA CORP·Filed 2023·Application pending·0 cites
- 1764US11869483B2Unsupervised alignment for text to speech synthesis using neural networksNVIDIA CORP·Filed 2021·Granted Jan 9, 2024·0 cites·20 claims
- 1864US11769481B2Unsupervised alignment for text to speech synthesis using neural networksNVIDIA CORP·Filed 2021·Granted Sep 26, 2023·0 cites·18 claims
- 1963US2022222778A1Upsampling an image using one or more neural networksNVIDIA CORP·Filed 2022·Application pending·0 cites
- 2060US12394113B2Pixel blending for neural network-based image generationNVIDIA CORP·Filed 2021·Granted Aug 19, 2025·0 cites·30 claims
- 2160US12340484B2Techniques to use a neural network to expand an imageNVIDIA CORP·Filed 2020·Granted Jun 24, 2025·0 cites·4 claims
- 2260US2022114702A1Upsampling an image using one or more neural networksNVIDIA CORP·Filed 2021·Application pending·0 cites
- 2358US12387028B2Data path circuit design using reinforcement learningNVIDIA CORP·Filed 2021·Granted Aug 12, 2025·0 cites·20 claims
- 2458US2022114701A1Upsampling an image using one or more neural networksNVIDIA CORP·Filed 2021·Application pending·0 cites
- 2557US2025117625A1Circuit prediction using neural networksNVIDIA CORP·Filed 2023·Application pending·0 cites
- 2655US12425605B2Image in-painting for irregular holes using partial convolutionsNVIDIA CORP·Filed 2019·Granted Sep 23, 2025·0 cites·20 claims
- 2755US2024095880A1Using a neural network to generate an upsampled imageNVIDIA CORP·Filed 2022·Application pending·0 cites
- 2854US2024161250A1Techniques for denoising diffusion using an ensemble of expert denoisersNVIDIA CORP·Filed 2023·Application pending·0 cites
- 2951US2025118286A1Synthesizing speech in multiple languages in conversational ai systems and applicationsNVIDIA CORP·Filed 2023·Application pending·0 cites
- 3050US2023035306A1Synthesizing video from audio using one or more neural networksNVIDIA CORP·Filed 2021·Application pending·0 cites
- 3149US2022012536A1Creating an image utilizing a map representing different classes of pixelsNVIDIA CORP·Filed 2021·Application pending·0 cites
- 3248US2022138903A1Upsampling an image using one or more neural networksNVIDIA CORP·Filed 2020·Application pending·0 cites
- 3348US2022148256A1Image blending using one or more neural networksNVIDIA CORP·Filed 2020·Application pending·0 cites
- 3447US2022180528A1Disentanglement of image attributes using a neural networkNVIDIA CORP·Filed 2022·Application pending·0 cites
- 3546US2024098216A1Video frame blendingNVIDIA CORP·Filed 2022·Application pending·0 cites
- 3645US8275805B2Method of decreasing a total computation time for a visual simulation loop in a virtual world applicationCHHUGANI JATIN·Filed 2010·Granted Sep 25, 2012·0 cites·19 claims
- 3745US2024095460A1Dialogue systems using knowledge bases and language models for automotive systems and applicationsNVIDIA CORP·Filed 2022·Application pending·0 cites
- 3844US2022130013A1Training one or more neural networks using synthetic dataNVIDIA CORP·Filed 2020·Application pending·0 cites
- 3943US2020394994A1Invertible neural network to synthesize audio signalsNVIDIA CORP·Filed 2019·Application pending·0 cites
- 4042US2022038653A1Techniques to generate interpolated video framesNVIDIA CORP·Filed 2020·Application pending·0 cites
- 4141US2024095447A1Neural network-based language restrictionNVIDIA CORP·Filed 2022·Application pending·0 cites
- 4241US2014149480A1System, method, and computer program product for transposing a matrixNVIDIA CORP·Filed 2013·Application pending·0 cites
- 4341US2022101494A1Fourier transform-based image synthesis using neural networksNVIDIA CORP·Filed 2020·Application pending·0 cites
- 4441US2021067735A1Video interpolation using one or more neural networksNVIDIA CORP·Filed 2019·Application pending·0 cites
- 4539US2019147296A1Creating an image utilizing a map representing different classes of pixelsNVIDIA CORP·Filed 2018·Application pending·0 cites
- 4639US2025106355A1Adaptive video frame blendingNVIDIA CORP·Filed 2022·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Bryan Catanzaro files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →