Patents by Inventor Matthew Shannon
Matthew Shannon 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: 20220101826Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.Type: ApplicationFiled: December 9, 2021Publication date: March 31, 2022Applicant: Google LLCInventors: Eric Dean Battenberg, Daisy Stanton, Russell John Wyatt Skerry-Ryan, Soroosh Mariooryad, David Teh-Hwa Kao, Thomas Edward Bagby, Sean Matthew Shannon
-
Patent number: 11222621Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.Type: GrantFiled: May 20, 2020Date of Patent: January 11, 2022Assignee: Google LLCInventors: Eric Dean Battenberg, Daisy Stanton, Russell John Wyatt Skerry-Ryan, Soroosh Mariooryad, David Teh-hwa Kao, Thomas Edward Bagby, Sean Matthew Shannon
-
Publication number: 20210379414Abstract: A system, management device, SCBA and wearable device are provided. In one or more embodiments, a wearable device for use with a self-contained breathing apparatus (SCBA) is provided. The device includes device processing circuitry configured to: determine a wireless personal accountability report (PAR) signal has been received, and transition into an alarm state based on the received wireless PAR signal. The alarm state configured to trigger at least one notification while in the alarm state where the triggering of at least one notification is configured to recur until an indication is received.Type: ApplicationFiled: October 7, 2019Publication date: December 9, 2021Inventors: Jerome Shanko, Jr., Jason R. CANNON, William E. PARSON, Wesley M. BARBEE, Matthew SHANNON, Michael S. SABOLCIK
-
Publication number: 20210366255Abstract: A system, wearable device and management device provided for predicting a flashover event. According to one aspect of the disclosure, a wearable device for predicting a flashover event is provided. The wearable device includes at least one thermal sensor configured to generate thermal data associated with an environment, and processing circuitry configured to: determine a risk of ignition of at least one combustible gas in the environment based on the thermal data, and trigger at least one action based on the determined risk of ignition.Type: ApplicationFiled: November 13, 2019Publication date: November 25, 2021Inventors: Andrew LONG, Panagiotis D. STANITSAS, Jerome SHANKO, Jr., Wesley M. BARBEE, Matthew M. SHETTEL, Matthew SHANNON, Johnathan R. GRAVES, James W. HOWARD, James B. SNYDER, James L.C. WERNESS, Jr., Jason PATTERSON, Ravi Raagav SRINIVAS, Payas TIKOTEKAR
-
Publication number: 20210195730Abstract: An user interface device includes a lens with a top surface and a bottom surface, where the bottom surface includes at least one graphic that is visible through the top surface of the lens. The user interface device further includes a transparent circuit film with a top surface and a bottom surface, at least one light emitting diode (LED), at least one silver conductor, and a layer of transparent pressure-sensitive adhesive that secures the bottom surface of the lens to the top surface of the transparent circuit film.Type: ApplicationFiled: December 10, 2018Publication date: June 24, 2021Applicant: Molex, LLCInventors: Steven FULTON, Matthew SHANNON
-
Publication number: 20210142174Abstract: A method for training an endpointer model includes short-form speech utterances and long-form speech utterances. The method also includes providing a short-form speech utterance as input to a shared neural network, the shared neural network configured to learn shared hidden representations suitable for both voice activity detection (VAD) and end-of-query (EOQ) detection. The method also includes generating, using a VAD classifier, a sequence of predicted VAD labels and determining a VAD loss by comparing the sequence of predicted VAD labels to a corresponding sequence of reference VAD labels. The method also includes, generating, using an EOQ classifier, a sequence of predicted EOQ labels and determining an EOQ loss by comparing the sequence of predicted EOQ labels to a corresponding sequence of reference EOQ labels. The method also includes training, using a cross-entropy criterion, the endpointer model based on the VAD loss and the EOQ loss.Type: ApplicationFiled: January 20, 2021Publication date: May 13, 2021Applicant: Google LLCInventors: Shuo-yiin Chang, Bo Li, Gabor Simko, Maria Corolina Parada San Martin, Sean Matthew Shannon
-
Publication number: 20210076504Abstract: A method for creating a circuit assembly includes printing first conductive traces on a first side of a flexible substrate, printing second conductive traces on a second side of the flexible substrate opposite to the first side, and placing the flexible substrate on a first pallet with the first side facing up. The method includes printing conductive adhesive to form first contact pads on the first side, placing at least one first component onto the first contact pads, and removing the flexible substrate from the first pallet. The method includes placing the flexible substrate on a second pallet with the second side facing up, where the second pallet includes recessed areas or cut outs that align with the at least one first component, printing conductive adhesive to form second contact pads on the second side, and placing at least one second component onto the second contact pads.Type: ApplicationFiled: December 20, 2018Publication date: March 11, 2021Applicant: Molex, LLCInventors: Michael DEPPE, Matthew SHANNON, Steve R. MOSER
-
Patent number: 10929754Abstract: A method for training an endpointer model includes short-form speech utterances and long-form speech utterances. The method also includes providing a short-form speech utterance as input to a shared neural network, the shared neural network configured to learn shared hidden representations suitable for both voice activity detection (VAD) and end-of-query (EOQ) detection. The method also includes generating, using a VAD classifier, a sequence of predicted VAD labels and determining a VAD loss by comparing the sequence of predicted VAD labels to a corresponding sequence of reference VAD labels. The method also includes, generating, using an EOQ classifier, a sequence of predicted EOQ labels and determining an EOQ loss by comparing the sequence of predicted EOQ labels to a corresponding sequence of reference EOQ labels. The method also includes training, using a cross-entropy criterion, the endpointer model based on the VAD loss and the EOQ loss.Type: GrantFiled: December 11, 2019Date of Patent: February 23, 2021Assignee: Google LLCInventors: Shuo-yiin Chang, Bo Li, Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
-
Publication number: 20210035551Abstract: A system for generating an output audio signal includes a context encoder, a text-prediction network, and a text-to-speech (TTS) model. The context encoder is configured to receive one or more context features associated with current input text and process the one or more context features to generate a context embedding associated with the current input text. The text-prediction network is configured to process the current input text and the context embedding to predict, as output, a style embedding for the current input text. The style embedding specifies a specific prosody and/or style for synthesizing the current input text into expressive speech The TTS model is configured to process the current input text and the style embedding to generate an output audio signal of expressive speech of the current input text. The output audio signal has the specific prosody and/or style specified by the style embedding.Type: ApplicationFiled: July 16, 2020Publication date: February 4, 2021Applicant: Google LLCInventors: Daisy Stanton, Eric Dean Battenberg, Russell John Wyatt Skerry-Ryan, Soroosh Mariooryad, David Teh-Hwa Kao, Thomas Edward Bagby, Sean Matthew Shannon
-
Publication number: 20200372897Abstract: A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.Type: ApplicationFiled: May 20, 2020Publication date: November 26, 2020Applicant: Google LLCInventors: Eric Dean Battenberg, Daisy Stanton, Russell John Wyatt Skerry-Ryan, Soroosh Mariooryad, David Teh-hwa Kao, Thomas Edward Bagby, Sean Matthew Shannon
-
Publication number: 20200365142Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.Type: ApplicationFiled: May 28, 2020Publication date: November 19, 2020Inventors: Hasim Sak, Sean Matthew Shannon
-
Patent number: 10706840Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.Type: GrantFiled: December 19, 2017Date of Patent: July 7, 2020Assignee: Google LLCInventors: Hasim Sak, Sean Matthew Shannon
-
Publication number: 20200168242Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.Type: ApplicationFiled: January 31, 2020Publication date: May 28, 2020Applicant: Google LLCInventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
-
Publication number: 20200117996Abstract: A method for training an endpointer model includes short-form speech utterances and long-form speech utterances. The method also includes providing a short-form speech utterance as input to a shared neural network, the shared neural network configured to learn shared hidden representations suitable for both voice activity detection (VAD) and end-of-query (EOQ) detection. The method also includes generating, using a VAD classifier, a sequence of predicted VAD labels and determining a VAD loss by comparing the sequence of predicted VAD labels to a corresponding sequence of reference VAD labels. The method also includes, generating, using an EOQ classifier, a sequence of predicted EOQ labels and determining an EOQ loss by comparing the sequence of predicted EOQ labels to a corresponding sequence of reference EOQ labels. The method also includes training, using a cross-entropy criterion, the endpointer model based on the VAD loss and the EOQ loss.Type: ApplicationFiled: December 11, 2019Publication date: April 16, 2020Applicant: Google LLCInventors: Shuo-yiin Chang, Bo Li, Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
-
Patent number: 10593352Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.Type: GrantFiled: June 6, 2018Date of Patent: March 17, 2020Assignee: Google LLCInventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
-
Patent number: 10536528Abstract: A personal multimedia communication system and network for emergency services personnel includes a plurality of personal communication systems linked together and to a base station in a network. Each personal communication system includes a PDA device mounted on a PASS control console, a video camera mounted on the PDA device, a GPS unit, a microphone, and other electronic devices. The various electronic devices are all communicatively connected to the PDA device. Data from the various devices may be collected in the PDA device and wirelessly transmitted to any other node or device in the network, including other personal communication devices. Each personal communication device may serve as a repeater, thus providing a wireless communications link between a device located out of range of the base station.Type: GrantFiled: February 8, 2016Date of Patent: January 14, 2020Assignee: Scott Technologies, Inc.Inventors: Craig M. Parkulo, Wesley McChord Barbee, Jerald Robert Malin, Jeffrey Lynn Landis, Matthew Shannon
-
Publication number: 20190057683Abstract: Methods, systems, and apparatus for performing speech recognition. In some implementations, acoustic data representing an utterance is obtained. The acoustic data corresponds to time steps in a series of time steps. One or more computers process scores indicative of the acoustic data using a recurrent neural network to generate a sequence of outputs. The sequence of outputs indicates a likely output label from among a predetermined set of output labels. The predetermined set of output labels includes output labels that respectively correspond to different linguistic units and to a placeholder label that does not represent a classification of acoustic data. The recurrent neural network is configured to use an output label indicated for a previous time step to determine an output label for the current time step. The generated sequence of outputs is processed to generate a transcription of the utterance, and the transcription of the utterance is provided.Type: ApplicationFiled: December 19, 2017Publication date: February 21, 2019Inventors: Hasim Sak, Sean Matthew Shannon
-
Publication number: 20180350395Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.Type: ApplicationFiled: June 6, 2018Publication date: December 6, 2018Inventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
-
Publication number: 20160173610Abstract: A personal multimedia communication system and network for emergency services personnel includes a plurality of personal communication systems linked together and to a base station in a network. Each personal communication system includes a PDA device mounted on a PASS control console, a video camera mounted on the PDA device, a GPS unit, a microphone, and other electronic devices. The various electronic devices are all communicatively connected to the PDA device. Data from the various devices may be collected in the PDA device and wirelessly transmitted to any other node or device in the network, including other personal communication devices. Each personal communication device may serve as a repeater, thus providing a wireless communications link between a device located out of range of the base station.Type: ApplicationFiled: February 8, 2016Publication date: June 16, 2016Applicant: SCOTT TECHNOLOGIES, INC.Inventors: CRAIG M. PARKULO, WESLEY MCCHORD BARBEE, JERALD ROBERT MALIN, JEFFREY LYNN LANDIS, MATTHEW SHANNON
-
Patent number: 8755839Abstract: A personal multimedia communication system and network for emergency services personnel includes a plurality of personal communication systems linked together and to a base station in a network. Each personal communication system includes a PDA device mounted on a PASS control console, a video camera mounted on the PDA device, a GPS unit, a microphone, and other electronic devices. The various electronic devices are all communicatively connected to the PDA device. Data from the various devices may be collected in the PDA device and wirelessly transmitted to any other node or device in the network, including other personal communication devices. Each personal communication device may serve as a repeater, thus providing a wireless communications link between a device located out of range of the base station.Type: GrantFiled: May 23, 2008Date of Patent: June 17, 2014Assignee: STI Licensing Corp.Inventors: Craig Michael Parkulo, Wesley McChord Barbee, Jerald Robert Malin, Jeffrey Lynn Landis, Matthew Shannon