Patents by Inventor Ryan Rifkin
Ryan Rifkin 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: 11556584Abstract: There is disclosed a system, apparatus and methods for optimizing photo selection. When a photographer takes photos as requested in a shot list, the photos are automatically assigned a quality score which correlates to how prominently the photo would be displayed in an online search. The photos and the quality scores are displayed to the photographer so that when the photographer has shot a sufficiently high quality photo then the photographer can stop shooting. Photos with the highest quality scores are optimal. The shot lists include reference photos, and if a new photo has a higher quality score than the corresponding reference photo, the new photo becomes the reference photo.Type: GrantFiled: March 31, 2022Date of Patent: January 17, 2023Assignee: Aircam Inc.Inventors: Evan Rifkin, Ryan Rifkin, David Hopkins, Jonathan Angelo, Marcus Buffet
-
Publication number: 20220374468Abstract: There is disclosed a system, apparatus and methods for optimizing photo selection. When a photographer takes photos as requested in a shot list, the photos are automatically assigned a quality score which correlates to how prominently the photo would be displayed in an online search. The photos and the quality scores are displayed to the photographer so that when the photographer has shot a sufficiently high quality photo then the photographer can stop shooting. Photos with the highest quality scores are optimal. The shot lists include reference photos, and if a new photo has a higher quality score than the corresponding reference photo, the new photo becomes the reference photo.Type: ApplicationFiled: March 31, 2022Publication date: November 24, 2022Inventors: Evan Rifkin, Ryan Rifkin, David Hopkins, Jonathan Angelo, Marcus Buffet
-
Patent number: 11335328Abstract: Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.Type: GrantFiled: October 26, 2018Date of Patent: May 17, 2022Assignee: Google LLCInventors: Aren Jansen, Manoj Plakal, Richard Channing Moore, Shawn Hershey, Ratheet Pandya, Ryan Rifkin, Jiayang Liu, Daniel Ellis
-
Patent number: 11308153Abstract: There is disclosed a system, apparatus and methods for optimizing photo selection. When a photographer takes photos as requested in a shot list, the photos are automatically assigned a quality score which correlates to how prominently the photo would be displayed in an online search. The photos and the quality scores are displayed to the photographer so that when the photographer has shot a sufficiently high quality photo then the photographer can stop shooting. Photos with the highest quality scores are optimal. The shot lists include reference photos, and if a new photo has a higher quality score than the corresponding reference photo, the new photo becomes the reference photo.Type: GrantFiled: November 9, 2021Date of Patent: April 19, 2022Assignee: Aircam Inc.Inventors: Evan Rifkin, Ryan Rifkin, David Hopkins, Jonathan Angelo, Marcus Buffet
-
Publication number: 20210361227Abstract: The present disclosure provides systems and methods that generating health diagnostic information from an audio recording. A computing system can include a machine-learned health model comprising that includes a sound model trained to receive data descriptive of a patient audio recording and output sound description data. The computing system can include a diagnostic model trained to receive the sound description data and output a diagnostic score. The computing system can include at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the patient audio recording; inputting data descriptive of the patient audio recording into the sound model; receiving, as an output of the sound model, the sound description data; inputting the sound description data into the diagnostic model; and receiving, as an output of the diagnostic model, the diagnostic score.Type: ApplicationFiled: May 4, 2018Publication date: November 25, 2021Inventors: Katherine Chou, Michael Dwight Howell, Kasumi Widner, Ryan Rifkin, Henry George Wei, Daniel Ellis, Alvin Rajkomar, Aren Jansen, David Michael Parish, Michael Philip Brenner
-
Publication number: 20200349921Abstract: Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.Type: ApplicationFiled: October 26, 2018Publication date: November 5, 2020Inventors: Aren Jansen, Manoj Plakal, Richard Channing Moore, Shawn Hershey, Ratheet Pandya, Ryan Rifkin, Jiayang Liu, Daniel Ellis
-
Patent number: 10757532Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.Type: GrantFiled: April 23, 2019Date of Patent: August 25, 2020Assignee: Aircam Inc.Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin, David Hopkins
-
Publication number: 20200250515Abstract: Generally, the present disclosure is directed to systems and methods for improved optimization of machine-learned models. In particular, the present disclosure provides stochastic optimization algorithms that are both faster than widely used algorithms for fixed amounts of computation, and are also able to scale up substantially better as more computational resources become available. The stochastic optimization algorithms can be used with large batch sizes. As an example, in some implementations, the systems and methods of the present disclosure can implicitly compute the inverse hessian of each mini-batch of training data to produce descent directions.Type: ApplicationFiled: July 6, 2018Publication date: August 6, 2020Inventors: Ryan Rifkin, Ying Xiao, Shankar Krishnan
-
Patent number: 10672387Abstract: The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.Type: GrantFiled: December 12, 2017Date of Patent: June 2, 2020Assignee: GOOGLE LLCInventors: Richard Lyon, Christopher Hughes, Yuxuan Wang, Ryan Rifkin, Pascal Getreuer
-
Publication number: 20190253833Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.Type: ApplicationFiled: April 23, 2019Publication date: August 15, 2019Inventors: Ryan RIFKIN, Evan RIFKIN, Steve Lackenby, Alex Pronin, David Hopkins
-
Patent number: 10285004Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.Type: GrantFiled: March 20, 2018Date of Patent: May 7, 2019Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
-
Patent number: 10285005Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.Type: GrantFiled: November 13, 2018Date of Patent: May 7, 2019Assignee: Aircam Inc.Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin, David Hopkins
-
Publication number: 20190082293Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.Type: ApplicationFiled: November 13, 2018Publication date: March 14, 2019Inventors: Ryan RIFKIN, Evan RIFKIN, Steve Lackenby, Alex Pronin, David Hopkins
-
Publication number: 20190082290Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.Type: ApplicationFiled: March 20, 2018Publication date: March 14, 2019Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
-
Patent number: 10154374Abstract: There is disclosed herein a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the connections is maintained. Without input from a user, media is shared between the individual devices on the connections list and between the individual devices on the connections list and a remote server. Devices not included in the list of connections are blocked from accessing the media. Access to the media is available for a pre-determined period of time, after which time access to the media is blocked for all devices.Type: GrantFiled: June 12, 2018Date of Patent: December 11, 2018Assignee: Aircam Inc.Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin, David Hopkins
-
Publication number: 20180302745Abstract: There is disclosed herein a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the connections is maintained. Without input from a user, media is shared between the individual devices on the connections list and between the individual devices on the connections list and a remote server. Devices not included in the list of connections are blocked from accessing the media. Access to the media is available for a pre-determined period of time, after which time access to the media is blocked for all devices.Type: ApplicationFiled: June 12, 2018Publication date: October 18, 2018Inventors: Ryan RIFKIN, Evan RIFKIN, Steve Lackenby, Alex Pronin, David Hopkins
-
Patent number: 10091317Abstract: A method and apparatus for proximity-based content sharing on wireless devices is presented in which a first device having a wireless communication region surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices. In response to a user action data is pushed from the wireless device to other wireless devices in the region. Communication connections can also be formed between devices in the region and devices outside the region and data may be pushed to the devices outside the region. Users can block other devices either within the region or outside the region so that they do not receive pushed data.Type: GrantFiled: March 14, 2016Date of Patent: October 2, 2018Assignee: Aircam Inc.Inventors: Evan Rifkin, Ryan Rifkin, Alex Pronin, Steve Lackenby
-
Publication number: 20180197533Abstract: The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.Type: ApplicationFiled: December 12, 2017Publication date: July 12, 2018Inventors: Richard Lyon, Christopher Hughes, Yuxuan Wang, Ryan Rifkin, Pascal Getreuer
-
Patent number: 9961493Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.Type: GrantFiled: September 8, 2017Date of Patent: May 1, 2018Assignee: Aircam Inc.Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
-
Publication number: 20170013076Abstract: A method and apparatus for proximity-based content sharing on wireless devices is presented in which a first device having a wireless communication region surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices. In response to a user action data is pushed from the wireless device to other wireless devices in the region. Communication connections can also be formed between devices in the region and devices outside the region and data may be pushed to the devices outside the region. Users can block other devices either within the region or outside the region so that they do not receive pushed data.Type: ApplicationFiled: March 14, 2016Publication date: January 12, 2017Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin