Patents by Inventor Vijeta Avijeet

Vijeta Avijeet 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: 20250014568
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signal.
    Type: Application
    Filed: September 17, 2024
    Publication date: January 9, 2025
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20240404507
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Application
    Filed: August 16, 2024
    Publication date: December 5, 2024
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Patent number: 12118979
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Grant
    Filed: July 3, 2023
    Date of Patent: October 15, 2024
    Assignee: Telepathy Labs, Inc.
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Patent number: 12118980
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signal.
    Type: Grant
    Filed: July 3, 2023
    Date of Patent: October 15, 2024
    Assignee: Telepathy Labs, Inc.
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20240086793
    Abstract: An omni-channel, intelligent, proactive virtual agent system and method of use are provided by which a user may engage in a conversation with the agent to interact with structured and unstructured data of an enterprise that is stored in a domain-specific world model for the enterprise.
    Type: Application
    Filed: August 18, 2023
    Publication date: March 14, 2024
    Inventors: Stephen Brown, Martin Reber, Vijeta Avijeet, Josselyn Boudet
  • Publication number: 20230368775
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Application
    Filed: July 3, 2023
    Publication date: November 16, 2023
    Applicant: TELEPATHY LABS, INC.
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Publication number: 20230351999
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signal.
    Type: Application
    Filed: July 3, 2023
    Publication date: November 2, 2023
    Inventors: Martin Reber, Vijeta Avijeet
  • Patent number: 11775891
    Abstract: An omni-channel, intelligent, proactive virtual agent system and method of use are provided by which a user may engage in a conversation with the agent to interact with structured and unstructured data of an enterprise that is stored in a domain-specific world model for the enterprise.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: October 3, 2023
    Assignee: Telepathy Labs, Inc.
    Inventors: Stephen Brown, Martin Reber, Vijeta Avijeet, Josselyn Boudett
  • Patent number: 11741942
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Grant
    Filed: August 3, 2022
    Date of Patent: August 29, 2023
    Assignee: Telepathy Labs, Inc
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Patent number: 11735161
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Grant
    Filed: January 31, 2022
    Date of Patent: August 22, 2023
    Assignee: Telepathy Labs, Inc
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20220375452
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Application
    Filed: August 3, 2022
    Publication date: November 24, 2022
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Publication number: 20220328039
    Abstract: A speech processing system and a method therefor is provided. The speech processing system may capture one or more speech signals. Each of the one or more speech signals may include at least one dialogue uttered by a user. Dialogues may be extracted from the one or more speech signals. Frequently uttered dialogues may be identified over a period of time. The frequently uttered dialogues may be a set of dialogues that are uttered by the user a number of times during the period of time more than other dialogues uttered by the user during the period of time. A local language model and a local acoustic model may be generated based on, at least in part, the frequently uttered dialogues. The one or more speech signals may be processed based on, at least in part, the local language model and the local acoustic model.
    Type: Application
    Filed: August 27, 2020
    Publication date: October 13, 2022
    Inventor: Vijeta Avijeet
  • Patent number: 11450307
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Grant
    Filed: March 27, 2019
    Date of Patent: September 20, 2022
    Assignee: TELEPATHY LABS, INC.
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Publication number: 20220148564
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Application
    Filed: January 31, 2022
    Publication date: May 12, 2022
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20220130378
    Abstract: A method and speech processing system for communicating with a user is provided. A speech signal may be received. The received speech signal may be processed by a first unified neural network to extract one or more of intents and entities. The one or more of intents and entities may be analyzed to generate a dialogue response. A second unified neural network may generate a speech output corresponding to the dialogue response for the user. In another example, a single unified neural network may process the received speech signal to extract one or more of intents and entities. The one or more of intents and entities may be analyzed, by the single unified neural network, to generate a dialogue response. The single unified neural network may generate a speech output corresponding to the dialogue response for the user.
    Type: Application
    Filed: December 20, 2019
    Publication date: April 28, 2022
    Inventor: Vijeta Avijeet
  • Patent number: 11244670
    Abstract: A technique proves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Grant
    Filed: June 20, 2019
    Date of Patent: February 8, 2022
    Assignee: TELEPATHY LABS, INC.
    Inventors: Martin Reber, Vijeta Avijeet
  • Patent number: 11244669
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Grant
    Filed: June 20, 2019
    Date of Patent: February 8, 2022
    Assignee: TELEPATHY LABS, INC.
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20210366460
    Abstract: A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.
    Type: Application
    Filed: March 27, 2019
    Publication date: November 25, 2021
    Inventors: Piero Perucci, Martin Reber, Vijeta Avijeet
  • Publication number: 20190304434
    Abstract: A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Application
    Filed: June 20, 2019
    Publication date: October 3, 2019
    Inventors: Martin Reber, Vijeta Avijeet
  • Publication number: 20190304435
    Abstract: A technique proves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.
    Type: Application
    Filed: June 20, 2019
    Publication date: October 3, 2019
    Inventors: Martin Reber, Vijeta Avijeet