Patents by Inventor Kenneth W.D. Smith
Kenneth W.D. Smith 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: 20210303273Abstract: A method, computer program product, and computing system for enabling the development of a conversational application within a first environment; and enabling the deployment of the conversational application within a second environment.Type: ApplicationFiled: October 14, 2020Publication date: September 30, 2021Inventors: David Ardman, Andrew Matkin, Nirvana Tikku, Matthias Haack, Christopher A. Starbird, John B. Fisler, Bartosz Adamczyk, Kenneth W. D. Smith, Simon Falardeau, Imad Obeid
-
Patent number: 11024298Abstract: Methods and apparatus for performing speech recognition using a garbage model. The method comprises receiving audio comprising speech and processing at least some of the speech using a garbage model to produce a garbage speech recognition result. The garbage model includes a plurality of sub-words, each of which corresponds to a possible combination of phonemes in a particular language.Type: GrantFiled: July 18, 2019Date of Patent: June 1, 2021Assignee: Nuance Communications, Inc.Inventors: Cosmin Popovici, Kenneth W. D. Smith, Petrus C. Cools
-
Patent number: 10789426Abstract: Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.Type: GrantFiled: October 22, 2018Date of Patent: September 29, 2020Assignee: Nuance Communications, Inc.Inventors: Jean-Francois Lavallee, Kenneth W. D. Smith
-
Publication number: 20200143799Abstract: Methods and apparatus for performing speech recognition using a garbage model. The method comprises receiving audio comprising speech and processing at least some of the speech using a garbage model to produce a garbage speech recognition result. The garbage model includes a plurality of sub-words, each of which corresponds to a possible combination of phonemes in a particular language.Type: ApplicationFiled: July 18, 2019Publication date: May 7, 2020Applicant: Nuance Communications, Inc.Inventors: Cosmin Popovici, Kenneth W.D. Smith, Petrus C. Cools
-
Publication number: 20190228065Abstract: Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.Type: ApplicationFiled: October 22, 2018Publication date: July 25, 2019Inventors: Jean-Francois Lavallee, Kenneth W. D. Smith
-
Patent number: 10360904Abstract: Methods and apparatus for performing speech recognition using a garbage model. The method comprises receiving audio comprising speech and processing at least some of the speech using a garbage model to produce a garbage speech recognition result. The garbage model includes a plurality of sub-words, each of which corresponds to a possible combination of phonemes in a particular language.Type: GrantFiled: May 9, 2014Date of Patent: July 23, 2019Assignee: Nuance Communications, Inc.Inventors: Cosmin Popovici, Kenneth W. D. Smith, Petrus C. Cools
-
Patent number: 10108603Abstract: Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.Type: GrantFiled: June 29, 2015Date of Patent: October 23, 2018Assignee: Nuance Communications, Inc.Inventors: Jean-Francois Lavallee, Kenneth W. D. Smith
-
Publication number: 20170076718Abstract: Methods and apparatus for performing speech recognition using a garbage model. The method comprises receiving audio comprising speech and processing at least some of the speech using a garbage model to produce a garbage speech recognition result. The garbage model includes a plurality of sub-words, each of which corresponds to a possible combination of phonemes in a particular language.Type: ApplicationFiled: May 9, 2014Publication date: March 16, 2017Applicant: Nuance Communication, IncInventors: Cosmin Popovici, Kenneth W.D. Smith, Petrus C. Cools
-
Patent number: 9571645Abstract: A method for conducting a call between a caller and an interactive voice response (IVR) system, the caller using a device to conduct the call, the device configured to execute a virtual assistant, the method comprising using the virtual assistant to conduct the call at least in part by influencing the style of information provided to the caller during the call and/or the content of information passed between the device and the IVR system during the call.Type: GrantFiled: December 16, 2013Date of Patent: February 14, 2017Assignee: Nuance Communications, Inc.Inventors: Holger Quast, Kenneth W. D. Smith, Jean-Guy E. Dahan, Andrew D. Mauro
-
Publication number: 20160350280Abstract: Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.Type: ApplicationFiled: June 29, 2015Publication date: December 1, 2016Inventors: Jean-Francois Lavallee, Kenneth W.D. Smith
-
Patent number: 9288156Abstract: Embodiments disclosed herein enable scaling up and making advanced natural language (NLU) applications more robust. According to one embodiment, state(s) associated with a dialog session may be recorded to a non-transitory medium. The dialog session may be suspended after a given period of inactivity and later automatically awakened based on unique client, session, or device identifier, or any combination thereof. Memory and resources associated with the suspended session may be reclaimed, the memory and resources being otherwise held by the session during the period of inactivity, enabling higher density (e.g., a larger number of sessions supported). Embodiments disclosed herein obviate a need for sticky dialog sessions, enabling higher density, and may further failover protection and fault tolerance for the dialog sessions.Type: GrantFiled: April 2, 2015Date of Patent: March 15, 2016Assignee: Nuance Communications, Inc.Inventors: Kenneth W. D. Smith, Solomon Z. Lerner, Caroline Drouin, Shimol Shah
-
Publication number: 20150244642Abstract: Embodiments disclosed herein enable scaling up and making advanced natural language (NLU) applications more robust. According to one embodiment, state(s) associated with a dialog session may be recorded to a non-transitory medium. The dialog session may be suspended after a given period of inactivity and later automatically awakened based on unique client, session, or device identifier, or any combination thereof. Memory and resources associated with the suspended session may be reclaimed, the memory and resources being otherwise held by the session during the period of inactivity, enabling higher density (e.g., a larger number of sessions supported). Embodiments disclosed herein obviate a need for sticky dialog sessions, enabling higher density, and may further failover protection and fault tolerance for the dialog sessions.Type: ApplicationFiled: April 2, 2015Publication date: August 27, 2015Inventors: Kenneth W.D. Smith, Solomon Z. Lerner, Caroline Drouin, Shimol Shah
-
Patent number: 9075619Abstract: An embodiment of the present invention includes a method for creating a dialog system that provides a framework for creating a multi-modal dialog application and includes a runtime application package (RAP) enabling runtime media grammars, prompts, classifiers, and so forth, to be separate from a multi-modal dialog application that utilizes the RAP. Embodiments disclosed herein enable newly trained runtime media supporting the multi-modal dialog application to be deployed with ease, and to do so while a dialog service is in operation. Embodiments disclosed herein enable the multi-modal dialog application to be created, deployed, and maintained in an easy and flexible manner, saving an end-user that may be providing the multi-modal dialog application to customers both time and cost.Type: GrantFiled: January 15, 2013Date of Patent: July 7, 2015Assignee: Nuance Corporation, Inc.Inventors: Kenneth W. D. Smith, Solomon Z. Lerner, Gerard Nantel, Caroline Drouin
-
Publication number: 20150172463Abstract: A method for conducting a call between a caller and an interactive voice response (IVR) system, the caller using a device to conduct the call, the device configured to execute a virtual assistant, the method comprising using the virtual assistant to conduct the call at least in part by influencing the style of information provided to the caller during the call and/or the content of information passed between the device and the IVR system during the call.Type: ApplicationFiled: December 16, 2013Publication date: June 18, 2015Applicant: Nuance Communications, Inc.Inventors: Holger Quast, Kenneth W.D. Smith, Jean-Guy E. Dahan, Andrew D. Mauro
-
Patent number: 9047856Abstract: A speech server and methods provide audio stream analysis for tone detection in addition to speech recognition to implement an accurate and efficient answering machine detection strategy. By performing both tone detection and speech recognition in a single component, such as the speech server, the number of components for digital signal processing may be reduced. The speech server communicates tone events detected at the telephony level and enables voice applications to detect tone events consistently and provide consistent support and accuracy of both inbound and outbound voice applications independent of the hardware or geographical location of the telephony network. In addition, an improved opportunity for signaling of an appropriate moment for an application to leave a message is provided, thereby supporting automation.Type: GrantFiled: July 26, 2012Date of Patent: June 2, 2015Assignee: Nuance Communications, Inc.Inventors: Kenneth W. D. Smith, Jaques de Broin
-
Patent number: 9026659Abstract: Embodiments disclosed herein enable scaling up and making advanced natural language (NLU) applications more robust. According to one embodiment, state(s) associated with a dialog session may be recorded to a fixed medium. The dialog session may be suspended after a given period of inactivity and later automatically awakened based on unique client, session, or device identifier, or any combination thereof. Memory and resources associated with the suspended session may be reclaimed, the memory and resources being otherwise held by the session during the period of inactivity, enabling higher density (e.g., a larger number of sessions supported). Embodiments disclosed herein obviate a need for sticky dialog sessions, enabling higher density, and may further failover protection and fault tolerance for the dialog sessions.Type: GrantFiled: February 5, 2013Date of Patent: May 5, 2015Assignee: Nuance Communications, Inc.Inventors: Kenneth W. D. Smith, Solomon Z. Lerner, Caroline Drouin, Shimol Shah
-
Publication number: 20140223011Abstract: Embodiments disclosed herein enable scaling up and making advanced natural language (NLU) applications more robust. According to one embodiment, state(s) associated with a dialog session may be recorded to a fixed medium. The dialog session may be suspended after a given period of inactivity and later automatically awakened based on unique client, session, or device identifier, or any combination thereof. Memory and resources associated with the suspended session may be reclaimed, the memory and resources being otherwise held by the session during the period of inactivity, enabling higher density (e.g., a larger number of sessions supported). Embodiments disclosed herein obviate a need for sticky dialog sessions, enabling higher density, and may further failover protection and fault tolerance for the dialog sessions.Type: ApplicationFiled: February 5, 2013Publication date: August 7, 2014Applicant: NUANCE COMMUNICATIONS, INC.Inventors: Kenneth W.D. Smith, Solomon Z. Lerner, Caroline Drouin, Shimol Shah
-
Publication number: 20140201729Abstract: An embodiment of the present invention includes a method for creating a dialog system that provides a framework for creating a multi-modal dialog application and includes a runtime application package (RAP) enabling runtime media grammars, prompts, classifiers, and so forth, to be separate from a multi-modal dialog application that utilizes the RAP. Embodiments disclosed herein enable newly trained runtime media supporting the multi-modal dialog application to be deployed with ease, and to do so while a dialog service is in operation. Embodiments disclosed herein enable the multi-modal dialog application to be created, deployed, and maintained in an easy and flexible manner, saving an end-user that may be providing the multi-modal dialog application to customers both time and cost.Type: ApplicationFiled: January 15, 2013Publication date: July 17, 2014Applicant: NUANCE COMMUNICATIONS, INC.Inventors: Kenneth W. D. Smith, Solomon Z. Lerner, Gerard Nantel, Caroline Drouin
-
Publication number: 20140029733Abstract: A speech server and methods provide audio stream analysis for tone detection in addition to speech recognition to implement an accurate and efficient answering machine detection strategy. By performing both tone detection and speech recognition in a single component, such as the speech server, the number of components for digital signal processing may be reduced. The speech server communicates tone events detected at the telephony level and enables voice applications to detect tone events consistently and provide consistent support and accuracy of both inbound and outbound voice applications independent of the hardware or geographical location of the telephony network. In addition, an improved opportunity for signaling of an appropriate moment for an application to leave a message is provided, thereby supporting automation.Type: ApplicationFiled: July 26, 2012Publication date: January 30, 2014Applicant: Nuance Communications, Inc.Inventors: Kenneth W.D. Smith, Jaques de Broin