Patents by Inventor Guru Prakash
Guru Prakash 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: 20240096326Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.Type: ApplicationFiled: December 1, 2023Publication date: March 21, 2024Applicant: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Patent number: 11848018Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.Type: GrantFiled: May 31, 2022Date of Patent: December 19, 2023Assignee: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Publication number: 20230335117Abstract: A method includes receiving, as input to a speech recognition model, audio data corresponding to a spoken utterance. The method also includes performing, using the speech recognition model, speech recognition on the audio data by, at each of a plurality of time steps, encoding, using an audio encoder, the audio data corresponding to the spoken utterance into a corresponding audio encoding, and decoding, using a speech recognition joint network, the corresponding audio encoding into a probability distribution over possible output labels. At each of the plurality of time steps, the method also includes determining, using an intended query (IQ) joint network configured to receive a label history representation associated with a sequence of non-blank symbols output by a final softmax layer, an intended query decision indicating whether or not the spoken utterance includes a query intended for a digital assistant.Type: ApplicationFiled: March 20, 2023Publication date: October 19, 2023Applicant: Google LLCInventors: Shuo-yiin Chang, Guru Prakash Arumugam, Zelin Wu, Tara N. Sainath, Bo LI, Qiao Liang, Adam Stambler, Shyam Upadhyay, Manaal Faruqui, Trevor Strohman
-
Publication number: 20230201292Abstract: Disclosed is an herbal formulation for the prevention and management of Type 2 diabetes and associated risk factors containing an effective amount of a hydro-alcoholic extract of Salacia roxburghii and an hydro-alcoholic extract of Salacia oblonga. Also disclosed are methods of preparing the formulation and using the formulation for the prevention and management of Type 2 diabetes and associated risk factors.Type: ApplicationFiled: March 11, 2022Publication date: June 29, 2023Inventors: Khushbu Kumari, Guru Prakash
-
Publication number: 20230165924Abstract: The present invention relates to a herbal formulation for the prevention and management of COVID-19 comprising hydro-alcoholic and n-hexane extracts of Hippophae rhamnoides, and hydro-alcoholic extracts of Tinospora cordifolia and Occimum sanctum and the bio-molecules of the said plants regulate the ACE2 receptors in different organ system.Type: ApplicationFiled: February 25, 2022Publication date: June 1, 2023Inventors: Khushbu Kumari, Guru Prakash
-
Patent number: 11545147Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.Type: GrantFiled: May 2, 2019Date of Patent: January 3, 2023Assignee: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Publication number: 20220293101Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.Type: ApplicationFiled: May 31, 2022Publication date: September 15, 2022Applicant: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Patent number: 11361768Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.Type: GrantFiled: July 21, 2020Date of Patent: June 14, 2022Assignee: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Publication number: 20200349946Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.Type: ApplicationFiled: July 21, 2020Publication date: November 5, 2020Applicant: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Patent number: 10712779Abstract: Embodiments are generally directed to a unified chassis construction for an all in one computer. An embodiment of a computer system includes a computer sub-system to provide computer operation; a display sub-system to provide display operation; a unified plate, components installed in the unified plate including at least one or more computer sub-system components and one or more display sub-system components; and a display screen coupled with the unified plate.Type: GrantFiled: December 7, 2015Date of Patent: July 14, 2020Assignee: INTEL CORPORATIONInventors: Anand V. Reddy, Guru Prakash, Harish Jagadish, Arvind Sundaram
-
Publication number: 20190304459Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.Type: ApplicationFiled: May 2, 2019Publication date: October 3, 2019Inventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Patent number: 10311872Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.Type: GrantFiled: July 25, 2017Date of Patent: June 4, 2019Assignee: Google LLCInventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Publication number: 20190035390Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.Type: ApplicationFiled: July 25, 2017Publication date: January 31, 2019Inventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
-
Publication number: 20170255233Abstract: Embodiments are generally directed to a unified chassis construction for an all in one computer. An embodiment of a computer system includes a computer sub-system to provide computer operation; a display sub-system to provide display operation; a unified plate, components installed in the unified plate including at least one or more computer sub-system components and one or more display sub-system components; and a display screen coupled with the unified plate.Type: ApplicationFiled: December 7, 2015Publication date: September 7, 2017Inventors: ANAND V. REDDY, GURU PRAKASH, HARISH JAGADISH, ARVIND SUNDARAM
-
Patent number: 9551177Abstract: Techniques related to a hinge in a computing device are described herein. The techniques may include forming a shaft to move rotationally, and forming a sliding component to move translationally as a result of rotational movement of the shaft.Type: GrantFiled: December 26, 2013Date of Patent: January 24, 2017Assignee: Intel CorporationInventors: Krishnakumar Varadarajan, Harish Jagadish, Anand V. Reddy, Madhukar Patil, James Panakkal, Guru Prakash
-
Publication number: 20150184438Abstract: Techniques related to a hinge in a computing device are described herein. The techniques may include forming a shaft to move rotationally, and forming a sliding component to move translationally as a result of rotational movement of the shaft.Type: ApplicationFiled: December 26, 2013Publication date: July 2, 2015Inventors: Krishnakumar Varadarajan, Harish Jagadish, Anand V. Reddy, Madhukar Patil, James Panakkal, Guru Prakash
-
Patent number: 6362219Abstract: The present invention relates to a synergistic formulation useful for the control of wide spectrum of malarial infections, which comprises a pharmaceutically effective amount of dihydroartemisinin and a vegetable oil.Type: GrantFiled: November 2, 2000Date of Patent: March 26, 2002Assignee: Council of Scientific and Industrial ResearchInventors: Dharam Chand Jain, Rajendra Singh Bhakuni, Ram Prakash Sharma, Sushil Kumar, Guru Prakash Dutta
-
Patent number: 6326023Abstract: The present invention relates to a synergistic formulation comprising pharmaceutically effective amount of &agr;/&bgr; arteether and a neutralized refined vegetable oil suitable for administration by rectal route, method for the treatment of cerebral and comatose malaria and process for the preparation of the said formulation.Type: GrantFiled: March 28, 2000Date of Patent: December 4, 2001Assignee: Council of Scientific & Industrial ResearchInventors: Guru Prakash Dutta, Dharam Chand Jain, Ranjendra Singh Bhakuni, Sudhanshu Saxena, Sangeeta Dhawan, Suman Preet Singh Khanuja, Sushil Kumar, Renu Tripathi, Aseem Umesh, Nuzhat Kamal, Anil Kumar Dwivedi, Satyawan Singh
-
Patent number: 6214864Abstract: The present invention relates to a synergistic formulation useful for the control of wide spectrum of malarial infections, which comprises a pharmaceutically effective amount of dihydroartemisinin and a vegetable oil.Type: GrantFiled: March 5, 1999Date of Patent: April 10, 2001Assignee: Council of Scientific and Industrial ResearchInventors: Dharam Chand Jain, Rajendra Singh Bhakuni, Ram Prakash Sharma, Sushil Kumar, Guru Prakash Dutta