Patents by Inventor Rupal Patel
Rupal Patel 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: 11062698Abstract: Image-based machine learning approaches are used to classify audio data, such as speech data as authentic or otherwise. For example, audio data can be obtained and a visual representation of the audio data can be generated. The visual representation can include, for example, an image such as a spectrogram or other visual or electronic representation of the audio data. Before processing the image, the audio data and/or image may undergo various preprocessing techniques. Thereafter, the image representation of the audio data can be analyzed using a trained model to classify the audio data as authentic or otherwise.Type: GrantFiled: October 24, 2019Date of Patent: July 13, 2021Assignee: VocaliD, INC.Inventors: Rupal Patel, Geoffrey S Meltzner, Markus Toman
-
Patent number: 10799503Abstract: Disclosed herein are methods of treating cancer in a subject, wherein the subject is known to possess at least one genetic alteration in RET, comprising administering to the subject a therapeutically effective amount of N-[3-[(6,7-dimethoxy-4-quinazolinyl)oxy]phenyl]-N?-[5-(2,2,2-trifluoro-1, 1-dimethylethyl)-3-isoxazolyl]-urea, or a pharmaceutically acceptable salt thereof.Type: GrantFiled: November 29, 2017Date of Patent: October 13, 2020Assignee: IGNYTA, INC.Inventors: Jonathan Ee-Ren Lim, Pratik S. Multani, Richard Landin, Rupal Patel, Jennifer Wright Oliver
-
Publication number: 20200184955Abstract: Image-based machine learning approaches are used to classify audio data, such as speech data as authentic or otherwise. For example, audio data can be obtained and a visual representation of the audio data can be generated. The visual representation can include, for example, an image such as a spectrogram or other visual or electronic representation of the audio data. Before processing the image, the audio data and/or image may undergo various preprocessing techniques. Thereafter, the image representation of the audio data can be analyzed using a trained model to classify the audio data as authentic or otherwise.Type: ApplicationFiled: October 24, 2019Publication date: June 11, 2020Applicant: VocaliD, INC.Inventors: Rupal PATEL, Geoffrey S. MELTZNER, Markus TOMAN
-
Publication number: 20200069688Abstract: Disclosed herein are methods of treating cancer in a subject, wherein the subject is known to possess at least one genetic alteration in RET, comprising administering to the subject a therapeutically effective amount of N-[3-[(6,7-dimethoxy-4-quinazolinyl)oxy]phenyl]-N?-[5-(2,2,2-trifluoro-1, 1-dimethylethyl)-3-isoxazolyl]-urea, or a pharmaceutically acceptable salt thereof.Type: ApplicationFiled: November 29, 2017Publication date: March 5, 2020Applicant: IGNYTA, INC.Inventors: Jonathan Ee-Ren Lim, Pratik S. Multani, Richard Landin, Rupal A. Patel, Jennifer Wright Oliver
-
Patent number: 10504504Abstract: Image-based machine learning approaches are used to classify audio data, such as speech data as authentic or otherwise. For example, audio data can be obtained and a visual representation of the audio data can be generated. The visual representation can include, for example, an image such as a spectrogram or other visual or electronic representation of the audio data. Before processing the image, the audio data and/or image may undergo various preprocessing techniques. Thereafter, the image representation of the audio data can be analyzed using a trained model to classify the audio data as authentic or otherwise.Type: GrantFiled: December 7, 2018Date of Patent: December 10, 2019Assignee: VocaliD, INC.Inventors: Geoffrey S Meltzner, Rupal Patel, Markus Toman
-
Patent number: 9558734Abstract: A voice recipient may request a text-to-speech (TTS) voice that corresponds to an age or age range. An existing TTS voice or existing voice data may be used to create a TTS voice corresponding to the requested age by encoding the voice data to voice parameter values, transforming the voice parameter values using a voice-aging model, synthesizing voice data using the transformed parameter values, and then creating a TTS voice using the transformed voice data. The voice-aging model may model how one or more voice parameters of a voice change with age and may be created from voice data stored in a voice bank.Type: GrantFiled: April 26, 2016Date of Patent: January 31, 2017Assignee: VOCALID, INC.Inventors: Rupal Patel, Geoffrey Seth Meltzner
-
Publication number: 20160379622Abstract: A voice recipient may request a text-to-speech (TTS) voice that corresponds to an age or age range. An existing TTS voice or existing voice data may be used to create a TTS voice corresponding to the requested age by encoding the voice data to voice parameter values, transforming the voice parameter values using a voice-aging model, synthesizing voice data using the transformed parameter values, and then creating a TTS voice using the transformed voice data. The voice-aging model may model how one or more voice parameters of a voice change with age and may be created from voice data stored in a voice bank.Type: ApplicationFiled: April 26, 2016Publication date: December 29, 2016Inventors: Rupal Patel, Geoffrey Seth Meltzner
-
Patent number: 9336782Abstract: Voice data may be collected by a plurality of voice donors and stored in a voice bank. A voice donor may authenticate to a voice collection system to start a session to provide voice data. During the voice collection session, the voice donor may be presented with a sequence of prompts to speak and voice data may be transferred to a server. The received voice data may be processed to determine the speech units spoken by the voice donor and a count of speech units received from the voice donor may be updated. Feedback may be provided to the voice donor indicating, for example, a progress of the voice collection, a quality level of the voice data, or information about speech unit counts. The voice bank may be used to create TTS voices for voice recipients, create a model of voice aging, or for other applications.Type: GrantFiled: June 29, 2015Date of Patent: May 10, 2016Assignee: VOCALID, INC.Inventor: Rupal Patel
-
Publication number: 20090317470Abstract: This invention relates to an oramucosal pharmaceutical dosage form in the form of a wafer. The wafer comprises a porous, hydroscopic, muco-adhesive polymeric matrix with at least one desired pharmaceutically active compound added thereto. The polymer is selected from a number of polymers having different dissolution rates and, in use when taken orally, the matrix adheres to an oramucosal surface to dissolve over a predetermined period of time to release the pharmaceutically active compound. The invention also extends to a method of manufacturing an oramucosal pharmaceutical dosage form in the form of a wafer which involves freeze drying or lyophilisation.Type: ApplicationFiled: September 19, 2006Publication date: December 24, 2009Inventors: Rupal Patel, Viness Pillay, Michael Danckwerts
-
Publication number: 20030059811Abstract: The present invention provides methods of screening for ligands of target molecules. The methods of the present invention include assays in which a target molecule is subjected to denaturing conditions, and compounds are screened for the ability to alter the susceptibility of the target to unfolding. The methods of the present invention use fluorescence detection to determine that degree of unfolding of a target molecule. In some aspects of the present invention, fluorescence resonance energy transfer (FRET) is detected. In other aspects of the invention, fluorescence polarization (FP) is detected. In preferred embodiments, a target molecule such as a target protein is heated to a temperature, called TATLAS, at which at least a portion of the target molecule unfolds, in the presence of a test compound.Type: ApplicationFiled: June 13, 2002Publication date: March 27, 2003Inventors: Hakim Djaballah, Scott Rongey, Rupal Patel, Mei Mei Wang, Joseph Coyle, Bin Li, Stephen Worland