Patents by Inventor Amro El-Jaroudi
Amro El-Jaroudi 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: 10869629Abstract: A method of classifying a swallow of a subject includes obtaining vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and using a computer implemented deep learning classifier to classify the swallow based on the vibration data. Also, a system for classifying a swallow of a subject includes a computing device implementing a deep learning classifier. The computing device includes a processor apparatus structured and configured to receive vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and use the deep learning classifier to classify the swallow based on the vibration data. The deep learning classifier may comprise a single layer or a multi-layer Deep Belief network.Type: GrantFiled: August 15, 2017Date of Patent: December 22, 2020Assignee: University of Pittsburgh-Of die Commonwealth System of Higher EducationInventors: Ervin Sejdic, Amro El-Jaroudi, James Coyle, Joshua Dudik, Mingui Sun, Zhi-Hong Mao
-
Publication number: 20190167182Abstract: A method of classifying a swallow of a subject includes obtaining vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and using a computer implemented deep learning classifier to classify the swallow based on the vibration data. Also, a system for classifying a swallow of a subject includes a computing device implementing a deep learning classifier. The computing device includes a processor apparatus structured and configured to receive vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and use the deep learning classifier to classify the swallow based on the vibration data. The deep learning classifier may comprise a single layer or a multi-layer Deep Belief network.Type: ApplicationFiled: August 15, 2017Publication date: June 6, 2019Applicant: UNIVERSITY OF PITTSBURGH-OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATIONInventors: Ervin Sejdic, Amro El-Jaroudi, James Coyle, Joshua Dudik, Mingui Sun, Zhi-Hong Mao
-
Publication number: 20140288933Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response.Type: ApplicationFiled: June 10, 2014Publication date: September 25, 2014Inventors: Keith Braho, Amro El-Jaroudi, Jeffrey Pike
-
Patent number: 8756059Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response.Type: GrantFiled: December 30, 2010Date of Patent: June 17, 2014Assignee: Vocollect, Inc.Inventors: Keith Braho, Amro El-Jaroudi, Jeffrey Pike
-
Patent number: 8612235Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system according to the invention has several embodiments including: comparing the observed speech features to the models of the expected response separately from the usual hypothesis search in order to speed up the recognition system; modifying the usual hypothesis search to emphasize the expected response; updating and adapting the models when the recognized speech matches the expected response to improve the accuracy of the recognition system.Type: GrantFiled: June 8, 2012Date of Patent: December 17, 2013Assignee: Vocollect, Inc.Inventors: Keith Braho, Amro El-Jaroudi
-
Patent number: 8417185Abstract: A wireless device for use with speech recognition applications comprises a frame generator for generating successive frames from digitized original audio signals, the frames representing portions of the digitized audio signals. An autocorrelation circuit generates a set of coefficients for each frame, the coefficient set being reflective of spectral characteristics of the audio signal portion represented by the frame. In one embodiment, the autocorrelation coefficients may be used to predict the original audio signal to be subtracted from the original audio signals and to generate residual signals A Bluetooth transceiver is configured for transmitting the set of coefficients and/or residual signals as data to another device, which utilizes the coefficients for speech applications.Type: GrantFiled: December 16, 2005Date of Patent: April 9, 2013Assignee: Vocollect, Inc.Inventors: Keith Braho, Roger Graham Byford, Thomas S. Kerr, Amro El-Jaroudi
-
Patent number: 8374870Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: GrantFiled: March 9, 2011Date of Patent: February 12, 2013Assignee: Vocollect, Inc.Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Publication number: 20120245939Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system according to the invention has several embodiments including: comparing the observed speech features to the models of the expected response separately from the usual hypothesis search in order to speed up the recognition system; modifying the usual hypothesis search to emphasize the expected response; updating and adapting the models when the recognized speech matches the expected response to improve the accuracy of the recognition system.Type: ApplicationFiled: June 8, 2012Publication date: September 27, 2012Inventors: Keith Braho, Amro El-Jaroudi
-
Patent number: 8255219Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: GrantFiled: March 9, 2011Date of Patent: August 28, 2012Assignee: Vocollect, Inc.Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Patent number: 8200495Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system according to the invention has several embodiments including: comparing the observed speech features to the models of the expected response separately from the usual hypothesis search in order to speed up the recognition system; modifying the usual hypothesis search to emphasize the expected response; updating and adapting the models when the recognized speech matches the expected response to improve the accuracy of the recognition system.Type: GrantFiled: January 13, 2006Date of Patent: June 12, 2012Assignee: Vocollect, Inc.Inventors: Keith Braho, Amro El-Jaroudi
-
Publication number: 20110161083Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: ApplicationFiled: March 9, 2011Publication date: June 30, 2011Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Publication number: 20110161082Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: ApplicationFiled: March 9, 2011Publication date: June 30, 2011Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Patent number: 7949533Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: GrantFiled: March 21, 2007Date of Patent: May 24, 2011Assignee: Vococollect, Inc.Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Publication number: 20110093269Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response.Type: ApplicationFiled: December 30, 2010Publication date: April 21, 2011Inventors: Keith Braho, Amro El-Jaroudi, Jeffrey Pike
-
Patent number: 7865362Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response.Type: GrantFiled: February 4, 2005Date of Patent: January 4, 2011Assignee: Vocollect, Inc.Inventors: Keith Braho, Amro El-Jaroudi, Jeffrey Pike
-
Publication number: 20080031441Abstract: A system (100) and method (300) are disclosed for filtering signals. A system that incorporates teachings of the present disclosure may include, for example, a speech processor (102) having an audio system (212) for audibly transmitting a rendition of a message, and for removing a portion of the rendered message embedded in a received signal as a result of at least one among electrical and electrical-magnetic interference between the rendered message and the received signal, thereby generating a filtered received signal. The audio system can capture the received signal while audibly transmitting the rendered message. Additional embodiments are disclosed.Type: ApplicationFiled: August 7, 2006Publication date: February 7, 2008Applicant: VOCOLLECT, INC.Inventors: KEITH BRAHO, AMRO EL-JAROUDI
-
Publication number: 20070198269Abstract: A method for assessing a performance of a speech recognition system may include determining a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.Type: ApplicationFiled: March 21, 2007Publication date: August 23, 2007Inventors: Keith Braho, Jeffrey Pike, Amro El-Jaroudi, Lori Pike, Michael Laughery
-
Publication number: 20070143105Abstract: A wireless device for use with speech recognition applications comprises a frame generator for generating successive frames from digitized original audio signals, the frames representing portions of the digitized audio signals. An autocorrelation circuit generates a set of coefficients for each frame, the coefficient set being reflective of spectral characteristics of the audio signal portion represented by the frame. In one embodiment, the autocorrelation coefficients may be used to predict the original audio signal to be subtracted from the original audio signals and to generate residual signals A Bluetooth transceiver is configured for transmitting the set of coefficients and/or residual signals as data to another device, which utilizes the coefficients for speech applications.Type: ApplicationFiled: December 16, 2005Publication date: June 21, 2007Inventors: Keith Braho, Roger Byford, Thomas Kerr, Amro El-Jaroudi
-
Publication number: 20060178886Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system according to the invention has several embodiments including: comparing the observed speech features to the models of the expected response separately from the usual hypothesis search in order to speed up the recognition system; modifying the usual hypothesis search to emphasize the expected response; updating and adapting the models when the recognized speech matches the expected response to improve the accuracy of the recognition system.Type: ApplicationFiled: January 13, 2006Publication date: August 10, 2006Inventors: Keith Braho, Amro El-Jaroudi
-
Publication number: 20060178882Abstract: A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available. In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. The modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response.Type: ApplicationFiled: February 4, 2005Publication date: August 10, 2006Inventors: Keith Braho, Amro El-Jaroudi, Jeffrey Pike