Patents by Inventor Subham BISWAS
Subham BISWAS 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: 20240127790Abstract: A device may receive and convert audio data to text data in real-time, and may detect a network fluctuation that causes missing voice packets. The device may process partial text and context of the text data, with a model, to generate a new phrase, and may generate a response phoneme for the new phrase. The device may utilize a text embedding model to generate a text embedding for the response phoneme, and may process the audio data, with the model, to generate a target voice sequence. The device may utilize an audio embedding model to generate an audio embedding for the target voice sequence, and may combine the text embedding and the audio embedding to generate an embedding input vector. The device may process the embedding input vector, with an audio synthesis model, to generate a final voice response, and may provide the audio data and the final voice response.Type: ApplicationFiled: October 12, 2022Publication date: April 18, 2024Applicant: Verizon Patent and Licensing Inc.Inventors: Saurabh TAHILIANI, Subham BISWAS
-
Publication number: 20240121487Abstract: A video summary device may generate a textual summary of a transcription of a virtual event. The video summary device may generate a phonemic transcription of the textual summary and generate a text embedding based on the phonemic transcription. The video summary device may generate an audio embedding based on a target voice. The video summary device may generate an audio output of the phonemic transcription uttered by the target voice. The audio output may be generated based on the text embedding and the audio embedding. The video summary device may generate an image embedding based on video data of a target user. The image embedding may include information regarding images of facial movements of the target user. The video summary device may generate a video output of different facial movements of the target user uttering the phonemic transcription, based on the text embedding and the image embedding.Type: ApplicationFiled: December 19, 2023Publication date: April 11, 2024Applicant: Verizon Patent and Licensing Inc.Inventors: Subham BISWAS, Saurabh TAHILIANI
-
Publication number: 20240096075Abstract: A method may include receiving a number of images to train a first neural network, masking a portion of each of the images and inputting the masked images to the first neural network. The method may also include generating, by the first neural network, probable pixel values for pixels located in the masked portion of each of the plurality of images, forwarding the images including the probable pixel values to a second neural network and determining, by the second neural network, whether each of the probable pixel values is contextually suitable. The method may further include identifying pixels in each of the plurality of images that are not contextually suitable.Type: ApplicationFiled: September 21, 2022Publication date: March 21, 2024Inventors: Subham Biswas, Saurabh Tahiliani
-
Publication number: 20240086474Abstract: An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.Type: ApplicationFiled: November 15, 2023Publication date: March 14, 2024Applicant: VERIZON PATENT AND LICENSING INC.Inventors: Subham BISWAS, Bharatwaaj SHANKAR
-
Publication number: 20240080689Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.Type: ApplicationFiled: November 10, 2023Publication date: March 7, 2024Inventors: Subham Biswas, Bharatwaaj Shankar, Sudhakar X. Lanka, Eswara P. Somarouthu, Keerthi Gudur
-
Publication number: 20240037824Abstract: Techniques for generating emotionally-aware digital content are disclosed. In one embodiment, a method is disclosed comprising obtaining audio input, obtaining a textual representation of the audio input; using the textual representation of the audio input to identify an emotion corresponding to the audio input; generating an emotionally-aware facial representation in accordance with the textual representation and the identified emotion; using the emotionally-aware facial representation to generate one or more images comprising at least one facial expression corresponding to the identified emotion; and providing digital content comprising the one or more images.Type: ApplicationFiled: July 26, 2022Publication date: February 1, 2024Applicant: VERIZON PATENT AND LICENSING INC.Inventors: Subham BISWAS, Saurabh TAHILIANI
-
Patent number: 11889168Abstract: A video summary device may generate a textual summary of a transcription of a virtual event. The video summary device may generate a phonemic transcription of the textual summary and generate a text embedding based on the phonemic transcription. The video summary device may generate an audio embedding based on a target voice. The video summary device may generate an audio output of the phonemic transcription uttered by the target voice. The audio output may be generated based on the text embedding and the audio embedding. The video summary device may generate an image embedding based on video data of a target user. The image embedding may include information regarding images of facial movements of the target user. The video summary device may generate a video output of different facial movements of the target user uttering the phonemic transcription, based on the text embedding and the image embedding.Type: GrantFiled: July 11, 2022Date of Patent: January 30, 2024Assignee: Verizon Patent and Licensing Inc.Inventors: Subham Biswas, Saurabh Tahiliani
-
Publication number: 20240028403Abstract: In some implementations, a device may determine cluster arrangements of clusters of technicians to perform a job. The device may provide, as input to a model, input values corresponding to exogenous factors associated with the job and with the cluster arrangements. The device may receive, as an output from the model, forecast values corresponding to endogenous factor(s) associated with the cluster arrangements. The device may determine combined forecast values associated with the cluster arrangements. A combined forecast value associated with a particular cluster arrangement may be a combination of forecast value(s) corresponding to the endogenous factor(s) associated with the particular cluster arrangement. The device may identify a selected cluster arrangement having a lowest combined forecast value. The device may assign the job to one or more technicians associated with the selected cluster arrangement.Type: ApplicationFiled: July 25, 2022Publication date: January 25, 2024Applicant: Verizon Patent and Licensing Inc.Inventors: Subham BISWAS, Keerthivasan MADURAI
-
Publication number: 20240015371Abstract: A video summary device may generate a textual summary of a transcription of a virtual event. The video summary device may generate a phonemic transcription of the textual summary and generate a text embedding based on the phonemic transcription. The video summary device may generate an audio embedding based on a target voice. The video summary device may generate an audio output of the phonemic transcription uttered by the target voice. The audio output may be generated based on the text embedding and the audio embedding. The video summary device may generate an image embedding based on video data of a target user. The image embedding may include information regarding images of facial movements of the target user. The video summary device may generate a video output of different facial movements of the target user uttering the phonemic transcription, based on the text embedding and the image embedding.Type: ApplicationFiled: July 11, 2022Publication date: January 11, 2024Applicant: Verizon Patent and Licensing Inc.Inventors: Subham BISWAS, Saurabh TAHILIANI
-
Patent number: 11860957Abstract: An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.Type: GrantFiled: June 25, 2021Date of Patent: January 2, 2024Assignee: Verizon Patent and Licensing Inc.Inventors: Subham Biswas, Bharatwaaj Shankar
-
Patent number: 11832119Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.Type: GrantFiled: August 31, 2021Date of Patent: November 28, 2023Assignee: Verizon Patent and Licensing Inc.Inventors: Subham Biswas, Bharatwaaj Shankar, Sudhakar X. Lanka, Eswara P. Somarouthu, Keerthi Gudur
-
Patent number: 11825353Abstract: A system described herein may provide a technique for the assignment of Centralized Units (“CUs”) to Distributed Units (“DUs”) in a radio access network (“RAN”) that includes a distributed or hierarchical arrangement of network infrastructure equipment. Different groups of DUs may be modeled based on usage or traffic patterns, and complementary groups of DUs may be identified based on measures of usage that may vary with time. For example, one model associated with one group of DUs may experience relatively heavy usage during morning hours and light usage during evening hours, and another model associated with a complementary group of DUs may experience relatively light usage during morning hours and heavy usage during evening hours.Type: GrantFiled: November 29, 2021Date of Patent: November 21, 2023Assignee: Verizon Patent and Licensing Inc.Inventors: Seng Gan, Subham Biswas, Christopher A. Graffeo, Saurabh Tahiliani
-
Patent number: 11818293Abstract: In some implementations, a device may obtain data indicating a client activity, and may determine predictive level scores corresponding to predictive level options associated with the client activity. The device may transmit, to a client device, a selected predictive level option having a highest predictive level score. The device may receive, from the client device, a client query based on a rejection of the selected predictive level option, and may determine intent level scores corresponding to intent level options associated with the client query. The device may identify a selected intent level option having a highest intent level score and may initiate client experience(s) associated with the selected intent level option. The predictive level scores and/or the intent level scores may be determined based on historical training data associated with combinations of client activities, predictive level options, client queries, intent level options, client experiences, and associated success scores.Type: GrantFiled: June 14, 2022Date of Patent: November 14, 2023Assignee: Verizon Patent and Licensing Inc.Inventors: Subham Biswas, Keerthivasan Madurai
-
Patent number: 11750742Abstract: A device may receive audio data of a first call between a first user and a second user. The device may generate, based on the audio data, time series data associated with an audio signal of the first call and may process, using a first machine learning model, the time series data to generate first call insight information regarding one or more first insights associated with the first call. The device may process the audio data to generate image data associated with the audio signal and may process, using a second machine learning model, the image data to generate second call insight information regarding one or more second insights associated with the first call. The device may combine the first call insight information and the second call insight information to generate combined call insight information and cause an action to be performed based on the combined call insight information.Type: GrantFiled: September 8, 2022Date of Patent: September 5, 2023Assignee: Verizon Patent and Licensing Inc.Inventors: Subham Biswas, Saurabh Tahiliani
-
Publication number: 20230196131Abstract: A system described herein may receive a set of outputs of a first model, which have been generated by the first model based on a set of inputs, and identify a set of historical values that correspond to the set of inputs and the set of outputs. The inputs and the historical values may be associated with the same time series. The system may train a second model based on the set of inputs to the first model, the set of outputs of the first model, and the set of historical values that correspond to the set of inputs and the set of outputs. The system may determine, based on training the second model, a set of weights associated with the set of historical values; and refine the first model based on the set of weights associated with the set of historical value.Type: ApplicationFiled: December 22, 2021Publication date: June 22, 2023Applicant: Verizon Patent and Licensing Inc.Inventors: Kushal Singla, Subham Biswas
-
Publication number: 20230169990Abstract: Techniques for generating emotionally-aware audio, or voice, responses for a user interface of an application, such as an automated voice response application, are disclosed. In one embodiment, a method is disclosed comprising obtaining voice input from a user via an automated voice response user interface of an application, obtaining a textual representation of the voice input, using the textual representation of the voice input from a user to obtain a source emotion of the user, determining a response emotion using the source emotion, generating a response textual representation indicating textual content of the response, generating a frequency spectrum representation of the response in accordance with the response textual representation and the response emotion, using the frequency spectrum representation of the response to generate a voice response reflective of the textual content of the response and the response emotion, and communicating the response to the user via the user interface.Type: ApplicationFiled: December 1, 2021Publication date: June 1, 2023Applicant: VERIZON PATENT AND LICENSING INC.Inventors: Subham BISWAS, Saurabh TAHILIANI
-
Publication number: 20230171644Abstract: A system described herein may provide a technique for the assignment of Centralized Units (“CUs”) to Distributed Units (“DUs”) in a radio access network (“RAN”) that includes a distributed or hierarchical arrangement of network infrastructure equipment. Different groups of DUs may be modeled based on usage or traffic patterns, and complementary groups of DUs may be identified based on measures of usage that may vary with time. For example, one model associated with one group of DUs may experience relatively heavy usage during morning hours and light usage during evening hours, and another model associated with a complementary group of DUs may experience relatively light usage during morning hours and heavy usage during evening hours.Type: ApplicationFiled: November 29, 2021Publication date: June 1, 2023Applicant: Verizon Patent and Licensing Inc.Inventors: Seng Gan, Subham Biswas, Christopher A. Graffeo, Saurabh Tahiliani
-
Publication number: 20230065889Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.Type: ApplicationFiled: August 31, 2021Publication date: March 2, 2023Inventors: Subham Biswas, Bharatwaaj Shankar, Sudhakar X. Lanka, Eswar P. Somarouthu, Keerthi Gudur
-
Publication number: 20230058560Abstract: A device may receive audio data of a first call between a first user and a second user. The device may generate, based on the audio data, time series data associated with an audio signal of the first call and may process, using a first machine learning model, the time series data to generate first call insight information regarding one or more first insights associated with the first call. The device may process the audio data to generate image data associated with the audio signal and may process, using a second machine learning model, the image data to generate second call insight information regarding one or more second insights associated with the first call. The device may combine the first call insight information and the second call insight information to generate combined call insight information and cause an action to be performed based on the combined call insight information.Type: ApplicationFiled: September 8, 2022Publication date: February 23, 2023Applicant: Verizon Patent and Licensing Inc.Inventors: Subham BISWAS, Saurabh TAHILIANI
-
Publication number: 20230050134Abstract: Disclosed are embodiments for improving training data for machine learning (ML) models. In an embodiment, a method is disclosed where an augmentation engine receives a seed example, the seed example stored in a seed training data set; generates an encoded seed example of the seed example using an encoder; inputs the encoded seed example into a machine learning model and receives a candidate example generated by the machine learning model; determines that the candidate example is similar to the encoded seed example; and augments the seed training data set with the candidate example.Type: ApplicationFiled: August 11, 2021Publication date: February 16, 2023Applicant: VERIZON PATENT AND LICENSING INC.Inventors: Subham BISWAS, Saurabh TAHILIANI