Patents by Inventor Neeraj Gaur
Neeraj Gaur 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: 11495233Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.Type: GrantFiled: October 20, 2021Date of Patent: November 8, 2022Assignee: GOOGLE LLCInventors: Asaf Aharoni, Arun Narayanan, Nir Shabat, Parisa Haghani, Galen Tsai Chuang, Yaniv Leviathan, Neeraj Gaur, Pedro J. Moreno Mengibar, Rohit Prakash Prabhavalkar, Zhongdi Qu, Austin Severn Waters, Tomer Amiaz, Michiel A.U. Bacchiani
-
Publication number: 20220309340Abstract: A method for distilling one or more trained teacher automatic speech recognition (ASR) models into a multilingual student model includes receiving a plurality of teacher training examples and a plurality of student training examples. The method also includes training one or more teacher automatic speech recognition (ASR) models using the plurality of teacher training examples. Each teacher ASR model is configured to output a respective textual representation of a respective audio input. The method further includes generating a multi-lingual student ASR model by training the multi-lingual student ASR model using the plurality of student training examples and distilling the trained one or more teacher ASR models into the multilingual student ASR model using a tunable distillation loss weight. Each student ASR model is configured to receive an audio input and output a corresponding textual representation of the received audio input.Type: ApplicationFiled: December 7, 2021Publication date: September 29, 2022Applicant: Google LLCInventors: Isabel Leal, Neeraj Gaur, Parisa Haghani, Brian Farris, Bhuvana Ramabhadran, Manasa Prasad, Pedro J. Moreno Mengibar, Yun Zhu
-
Publication number: 20220310081Abstract: A method includes receiving a sequence of acoustic frames extracted from audio data corresponding to an utterance. During a first pass, the method includes processing the sequence of acoustic frames to generate N candidate hypotheses for the utterance. During a second pass, and for each candidate hypothesis, the method includes generating a respective un-normalized likelihood score; generating a respective external language model score; generating a standalone score that models prior statistics of the corresponding candidate hypothesis, and generating a respective overall score for the candidate hypothesis based on the un-normalized likelihood score, the external language model score, and the standalone score. The method also includes selecting the candidate hypothesis having the highest respective overall score from among the N candidate hypotheses as a final transcription of the utterance.Type: ApplicationFiled: March 22, 2022Publication date: September 29, 2022Applicant: Google LLCInventors: Neeraj Gaur, Tongzhou Chen, Ehsan Variani, Bhuvana Ramabhadran, Parisa Haghani, Pedro J. Moreno Mengibar
-
Publication number: 20220211705Abstract: The present invention relates to a tablet comprising Afatinib or a pharmaceutically acceptable salt thereof, wherein the tablet is obtained by direct compression. The present invention further relates to a process for manufacturing a tablet of the invention as well as the use of the tablet of the invention.Type: ApplicationFiled: March 22, 2022Publication date: July 7, 2022Applicant: FRESENIUS KABI ONCOLOGY LIMITEDInventors: Rajesh KHANNA, Neeraj KUMAR, Vijay Kumar SHARMA, Ankit GAUR, Dhiraj KHATTAR
-
Publication number: 20220198568Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customized financial advice. The system may receive transaction data for a transaction associated with a customer and satisfaction data associated with the transaction. Based on the received transaction data and satisfaction data, the system may update a financial state of the customer and a financial policy for determining one or more actions to take in order to maximize a cumulative reward associated with the customer. The system may determine and output a recommended action based on the updated financial policy and customer financial state.Type: ApplicationFiled: March 8, 2022Publication date: June 23, 2022Inventors: Rashan Jibowu, Brian Farris, Neeraj Gaur
-
Patent number: 11288748Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customized financial advice. The system may receive transaction data for a transaction associated with a customer and satisfaction data associated with the transaction. Based on the received transaction data and satisfaction data, the system may update a financial state of the customer and a financial policy for determining one or more actions to take in order to maximize a cumulative reward associated with the customer. The system may determine and output a recommended action based on the updated financial policy and customer financial state.Type: GrantFiled: February 17, 2020Date of Patent: March 29, 2022Assignee: CAPITAL ONE SERVICES, LLCInventors: Rashan Jibowu, Brian Farris, Neeraj Gaur
-
Publication number: 20220044684Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.Type: ApplicationFiled: October 20, 2021Publication date: February 10, 2022Inventors: Asaf Aharoni, Arun Narayanan, Nir Shabat, Parisa Haghani, Galen Tsai Chuang, Yaniv LEVIATHAN, Neeraj Gaur, Pedro J. Moreno Mengibar, Rohit Prakash Prabhavalkar, Zhongdi Qu, Austin Severn Waters, Tomer Amiaz, Michiel A.U. Bacchiani
-
Patent number: 11158321Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.Type: GrantFiled: September 24, 2019Date of Patent: October 26, 2021Assignee: GOOGLE LLCInventors: Asaf Aharoni, Arun Narayanan, Nir Shabat, Parisa Haghani, Galen Tsai Chuang, Yaniv Leviathan, Neeraj Gaur, Pedro J. Moreno Mengibar, Rohit Prakash Prabhavalkar, Zhongdi Qu, Austin Severn Waters, Tomer Amiaz, Michiel A. U. Bacchiani
-
Publication number: 20210090570Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.Type: ApplicationFiled: September 24, 2019Publication date: March 25, 2021Inventors: Asaf Aharoni, Arun Narayanan, Nir Shabat, Parisa Haghani, Galen Tsai Chuang, Yaniv Leviathan, Neeraj Gaur, Pedro J. Moreno Mengibar, Rohit Prakash Prabhavalkar, Zhongdi Qu, Austin Severn Waters, Tomer Amiaz, Michiel A.U. Bacchiani
-
Publication number: 20200184566Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customized financial advice. The system may receive transaction data for a transaction associated with a customer and satisfaction data associated with the transaction. Based on the received transaction data and satisfaction data, the system may update a financial state of the customer and a financial policy for determining one or more actions to take in order to maximize a cumulative reward associated with the customer. The system may determine and output a recommended action based on the updated financial policy and customer financial state.Type: ApplicationFiled: February 17, 2020Publication date: June 11, 2020Inventors: Rashan Jibowu, Brian Farris, Neeraj Gaur
-
Patent number: 10565655Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customized financial advice. The system may receive transaction data for a transaction associated with a customer and satisfaction data associated with the transaction. Based on the received transaction data and satisfaction data, the system may update a financial state of the customer and a financial policy for determining one or more actions to take in order to maximize a cumulative reward associated with the customer. The system may determine and output a recommended action based on the updated financial policy and customer financial state.Type: GrantFiled: August 1, 2017Date of Patent: February 18, 2020Assignee: CAPITAL ONE SERVICES, LLCInventors: Rashan Jibowu, Brian Farris, Neeraj Gaur
-
Publication number: 20180336636Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customized financial advice. The system may receive transaction data for a transaction associated with a customer and satisfaction data associated with the transaction. Based on the received transaction data and satisfaction data, the system may update a financial state of the customer and a financial policy for determining one or more actions to take in order to maximize a cumulative reward associated with the customer. The system may determine and output a recommended action based on the updated financial policy and customer financial state.Type: ApplicationFiled: August 1, 2017Publication date: November 22, 2018Inventors: Rashan Jibowu, Brian Farris, Neeraj Gaur
-
Patent number: 10123040Abstract: Video telephony (VT) call management techniques are described. The techniques enable a device to cache intra-frame data at a pre-decoder-initialization stage. An example device includes a memory configured to store video data associated with a VT call, a video decoder configured to render a portion of the stored video data; and one or more processors. The processor(s) are configured to determine whether the received video frame data comprises i-frame data, to determine whether the video decoder is in a pre-initialized state or an initialized state, and when the received video frame data comprises the i-frame data and the video decoder is in the pre-initialized state, to store the i-frame data to the memory.Type: GrantFiled: August 30, 2016Date of Patent: November 6, 2018Assignee: QUALCOMM IncorporatedInventors: Aditya Namjoshi, Harish Bhandiwad, Clayton Wong, Neeraj Gaur
-
Publication number: 20180063548Abstract: Video telephony (VT) call management techniques are described. The techniques enable a device to cache intra-frame data at a pre-decoder-initialization stage. An example device includes a memory configured to store video data associated with a VT call, a video decoder configured to render a portion of the stored video data; and one or more processors. The processor(s) are configured to determine whether the received video frame data comprises i-frame data, to determine whether the video decoder is in a pre-initialized state or an initialized state, and when the received video frame data comprises the i-frame data and the video decoder is in the pre-initialized state, to store the i-frame data to the memory.Type: ApplicationFiled: August 30, 2016Publication date: March 1, 2018Inventors: Aditya Namjoshi, Harish Bhandiwad, Clayton Wong, Neeraj Gaur
-
Publication number: 20170181215Abstract: Methods and devices for wireless communication are disclosed. For example, one method includes detecting a loss of connectivity between a user equipment and a network, the user equipment having at least a first and second layer of a communication protocol. The method further includes sending messages from the first layer to the second layer, at least one message of the messages being delayed at the second layer based on the loss of connectivity. The method also includes identifying, at the first layer, at least one trigger condition, determining, at the first layer, to abort the sending of a first delayed message to the network based on the identified at least one trigger condition, communicating, by the first layer, to the second layer the determination to abort the first delayed message; and aborting the sending of the first delayed message at the second layer.Type: ApplicationFiled: December 16, 2015Publication date: June 22, 2017Inventors: Neeraj Gaur, Ajith Payyappilly, Aditya Namjoshi, Ashish Agarwal, Liping Shen, Juan Zhang
-
Publication number: 20050070248Abstract: The present invention is a method and system for transferring copy-protected content stored on a current mobile device to a new mobile device. Copy-protected content may be stored in an encrypted format in a storage unit of a mobile device. Decryption of the encrypted copy-protected content into the volatile memory (RAM) of the mobile device may only occur upon the detection of digital rights information stored in a removable data card within the mobile device. When the user wishes to purchase a new or different mobile device, the encrypted copy-protected content stored in the storage unit of the current mobile device may be transferred to a storage unit of a new mobile device. The encrypted copy-protected content that has been transferred to the new mobile device may only be decrypted upon transfer of the data card of the current mobile device to the new mobile device.Type: ApplicationFiled: January 23, 2004Publication date: March 31, 2005Inventor: Neeraj Gaur