Patents by Inventor Pieter J. Vermeulen
Pieter J. Vermeulen 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: 10248770Abstract: Techniques for unobtrusively verifying the identity of a user of a computing device are provided. In one embodiment, the computing device can establish one or more verification models for verifying the user's identity, where at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user. The computing device can then verify the user's identity using the one or more verification models.Type: GrantFiled: August 4, 2014Date of Patent: April 2, 2019Assignee: Sensory, IncorporatedInventors: John-Paul Hosom, Todd F. Mozer, Pieter J. Vermeulen, Bryan L. Pellom
-
Patent number: 9548065Abstract: In one embodiment, a computing device can detect an utterance of a target phrase within an acoustic input signal. The computing device can further determine a first estimate of cumulative signal and noise energy for the detected utterance in the acoustic input signal with respect to a first time period spanning the duration of the detected utterance, and a second estimate of noise energy in the acoustic input signal with respect to a second time period preceding (or following) the first time period. The computing device can then calculate a signal-to-noise ratio (SNR) for the detected utterance based on the first and second estimates and can reject the detected utterance if the SNR is below an SNR threshold.Type: GrantFiled: May 5, 2014Date of Patent: January 17, 2017Assignee: Sensory, IncorporatedInventors: Pieter J. Vermeulen, John-Paul Hosom
-
Patent number: 9484028Abstract: In one embodiment the present invention includes a method comprising receiving an acoustic input signal and processing the acoustic input signal with a plurality of acoustic recognition processes configured to recognize the same target sound. Different acoustic recognition processes start processing different segments of the acoustic input signal at different time points in the acoustic input signal. In one embodiment, initial states in the recognition processes may be configured on each time step.Type: GrantFiled: February 19, 2014Date of Patent: November 1, 2016Assignee: Sensory, IncorporatedInventors: Pieter J. Vermeulen, Jonathan Shaw, Todd F. Mozer
-
Publication number: 20160046236Abstract: Techniques for enabling automated blind spot viewing in a vehicle are provided. In one embodiment, a computer system within the vehicle can determine that a driver of the vehicle is gazing at a side view mirror. The computer system can then automatically facilitate viewing of objects in the driver's blind spot in response to the determination.Type: ApplicationFiled: August 13, 2014Publication date: February 18, 2016Inventors: Todd F. Mozer, Pieter J. Vermeulen
-
Patent number: 9230550Abstract: In one embodiment, a computer system stores speech data for a plurality of speakers, where the speech data includes a plurality of feature vectors and, for each feature vector, an associated sub-phonetic class. The computer system then builds, based on the speech data, an artificial neural network (ANN) for modeling speech of a target speaker in the plurality of speakers, where the ANN is configured to discriminate between instances of sub-phonetic classes uttered by the target speaker and instances of sub-phonetic classes uttered by other speakers in the plurality of speakers.Type: GrantFiled: January 10, 2013Date of Patent: January 5, 2016Assignee: Sensory, IncorporatedInventors: John-Paul Hosom, Pieter J. Vermeulen, Jonathan Shaw
-
Publication number: 20150317980Abstract: In one embodiment, a computing device can detect an utterance of a target phrase within an acoustic input signal. The computing device can further determine a first estimate of cumulative signal and noise energy for the detected utterance in the acoustic input signal with respect to a first time period spanning the duration of the detected utterance, and a second estimate of noise energy in the acoustic input signal with respect to a second time period preceding (or following) the first time period. The computing device can then calculate a signal-to-noise ratio (SNR) for the detected utterance based on the first and second estimates and can reject the detected utterance if the SNR is below an SNR threshold.Type: ApplicationFiled: May 5, 2014Publication date: November 5, 2015Applicant: SENSORY, INCORPORATEDInventors: Pieter J. Vermeulen, John-Paul Hosom
-
Publication number: 20150261944Abstract: Techniques for unobtrusively verifying the identity of a user of a computing device are provided. In one embodiment, the computing device can establish one or more verification models for verifying the user's identity, where at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user. The computing device can then verify the user's identity using the one or more verification models.Type: ApplicationFiled: August 4, 2014Publication date: September 17, 2015Inventors: John-Paul Hosom, Todd F. Mozer, Pieter J. Vermeulen, Bryan L. Pellom
-
Publication number: 20140195236Abstract: In one embodiment, a computer system stores speech data for a plurality of speakers, where the speech data includes a plurality of feature vectors and, for each feature vector, an associated sub-phonetic class. The computer system then builds, based on the speech data, an artificial neural network (ANN) for modeling speech of a target speaker in the plurality of speakers, where the ANN is configured to discriminate between instances of sub-phonetic classes uttered by the target speaker and instances of sub-phonetic classes uttered by other speakers in the plurality of speakers.Type: ApplicationFiled: January 10, 2013Publication date: July 10, 2014Applicant: Sensory, IncorporatedInventors: John-Paul Hosom, Pieter J. Vermeulen, Jonathan Shaw
-
Publication number: 20140180691Abstract: In one embodiment the present invention includes a method comprising receiving an acoustic input signal and processing the acoustic input signal with a plurality of acoustic recognition processes configured to recognize the same target sound. Different acoustic recognition processes start processing different segments of the acoustic input signal at different time points in the acoustic input signal. In one embodiment, initial states in the recognition processes may be configured on each time step.Type: ApplicationFiled: February 19, 2014Publication date: June 26, 2014Applicant: SENSORY, INCORPORATEDInventors: Pieter J. Vermeulen, Jonathan Shaw, Todd F. Mozer
-
Patent number: 8700399Abstract: In one embodiment the present invention includes a method comprising receiving an acoustic input signal and processing the acoustic input signal with a plurality of acoustic recognition processes configured to recognize the same target sound. Different acoustic recognition processes start processing different segments of the acoustic input signal at different time points in the acoustic input signal. In one embodiment, initial states in the recognition processes may be configured on each time step.Type: GrantFiled: July 6, 2010Date of Patent: April 15, 2014Assignee: Sensory, Inc.Inventors: Pieter J. Vermeulen, Jonathan Shaw, Todd F. Mozer
-
Patent number: 8645132Abstract: Embodiments of the present invention improve content manipulation systems and methods using speech recognition. In one embodiment, the present invention includes a method comprising configuring a recognizer to recognize utterances in the presence of a background audio signal having particular audio characteristics. A composite signal comprising a first audio signal and a spoken utterance of a user is received by the recognizer, where the first audio signal comprises the particular audio characteristics used to configure the recognizer so that the recognizer is desensitized to the first audio signal. The spoke utterance is recognized in the presence of the first audio signal when the spoken utterance is one of the predetermined utterances. An operation is performed on the first audio signal.Type: GrantFiled: August 24, 2011Date of Patent: February 4, 2014Assignee: Sensory, Inc.Inventors: Todd F. Mozer, Jeff Rogers, Pieter J. Vermeulen, Jonathan Shaw
-
Publication number: 20130054235Abstract: Embodiments of the present invention improve content manipulation systems and methods using speech recognition. In one embodiment, the present invention includes a method comprising configuring a recognizer to recognize utterances in the presence of a background audio signal having particular audio characteristics. A composite signal comprising a first audio signal and a spoken utterance of a user is received by the recognizer, where the first audio signal comprises the particular audio characteristics used to configure the recognizer so that the recognizer is desensitized to the first audio signal. The spoke utterance is recognized in the presence of the first audio signal when the spoken utterance is one of the predetermined utterances. An operation is performed on the first audio signal.Type: ApplicationFiled: August 24, 2011Publication date: February 28, 2013Applicant: Sensory, IncorporatedInventors: Todd F. Mozer, Jeff Rogers, Pieter J. Vermeulen, Jonathan Shaw
-
Publication number: 20110166855Abstract: In one embodiment the present invention includes a method comprising receiving an acoustic input signal and processing the acoustic input signal with a plurality of acoustic recognition processes configured to recognize the same target sound. Different acoustic recognition processes start processing different segments of the acoustic input signal at different time points in the acoustic input signal. In one embodiment, initial states in the recognition processes may be configured on each time step.Type: ApplicationFiled: July 6, 2010Publication date: July 7, 2011Applicant: SENSORY, INCORPORATEDInventors: Pieter J. Vermeulen, Jonathan Shaw, Todd F. Mozer
-
Patent number: 7720683Abstract: A speech recognition technique is described that has the dual benefits of not requiring collection of recordings for training while using computational resources that are cost-compatible with consumer electronic products. Methods are described for improving the recognition accuracy of a recognizer by developer interaction with a design tool that iterates the recognition data during development of a recognition set of utterances and that allows controlling and minimizing the computational resources required to implement the recognizer in hardware.Type: GrantFiled: June 10, 2004Date of Patent: May 18, 2010Assignee: Sensory, Inc.Inventors: Pieter J. Vermeulen, Robert E. Savoie, Stephen Sutton, Forrest S. Mozer