Patents by Inventor Kevin R. Farrell
Kevin R. Farrell 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: 20210050024Abstract: An audio watermark is embedded in synthetic speech, such as synthetic speech created using text-to-speech (TTS) synthesis. Such audio watermarks can, for example, be used to increase the accuracy of voice biometric (VB) and other systems in distinguishing synthetic speech from human speech. In addition to its use in voice biometrics, such audio watermarking can prevent misuse of human quality TTS, or other synthetic speech, in a variety of other contexts, such as incriminating recordings, spam messages, contact center denial of service, and protection of personal information in contact centers not utilizing VB.Type: ApplicationFiled: August 12, 2019Publication date: February 18, 2021Inventors: Johan Wouters, Kevin R. Farrell, William F. Ganong, III
-
Patent number: 10529338Abstract: Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing.Type: GrantFiled: June 26, 2018Date of Patent: January 7, 2020Assignee: Nuance Communications, Inc.Inventors: Almog Aley-Raz, Kevin R. Farrell, Oshrit Yaron, Luca Scarpato
-
Publication number: 20190035406Abstract: Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing.Type: ApplicationFiled: June 26, 2018Publication date: January 31, 2019Inventors: Almog Aley-Raz, Kevin R. Farrell, Oshrit Yaron, Luca Scarpato
-
Patent number: 10008208Abstract: Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing.Type: GrantFiled: September 18, 2014Date of Patent: June 26, 2018Assignee: Nuance Communications, Inc.Inventors: Almog Aley-Raz, Kevin R. Farrell, Oshrit Yaron, Luca Scarpato
-
Patent number: 9865266Abstract: Typical speaker verification systems usually employ speakers' audio data collected during an enrollment phase when users enroll with the system and provide respective voice samples. Due to technical, business, or other constraints, the enrollment data may not be large enough or rich enough to encompass different inter-speaker and intra-speaker variations. According to at least one embodiment, a method and apparatus employing classifier adaptation based on field data in a deployed voice-based interactive system comprise: collecting representations of voice characteristics, in association with corresponding speakers, the representations being generated by the deployed voice-based interactive system; updating parameters of the classifier, used in speaker recognition, based on the representations collected; and employing the classifier, with the corresponding parameters updated, in performing speaker recognition.Type: GrantFiled: February 25, 2013Date of Patent: January 9, 2018Assignee: Nuance Communications, Inc.Inventors: Daniele Ernesto Colibro, Claudio Vair, Kevin R. Farrell
-
Patent number: 9728191Abstract: Techniques for automatically identifying a speaker in a conversation as a known person based on processing of audio of the speaker's voice to extract characteristics of that voice and on an automated comparison of those characteristics to known characteristics of the known person's voice. A speaker segmentation process may be performed on audio of the conversation to produce, for each speaker in the conversation, a segment that includes the audio of that speaker. Audio of each of the segments may then be processed to extract characteristics of that speaker's voice. The characteristics derived from each segment (and thus for multiple speakers) may then be compared to characteristics of the known person's voice to determine whether the speaker for that segment is the known person. For each segment, a degree of match between the voice characteristics of the speaker and the voice characteristics of the known person may be calculated.Type: GrantFiled: August 27, 2015Date of Patent: August 8, 2017Assignee: Nuance Communications, Inc.Inventors: Emanuele Dalmasso, Daniele Colibro, Claudio Vair, Kevin R. Farrell
-
Publication number: 20170061968Abstract: Techniques for automatically identifying a speaker in a conversation as a known person based on processing of audio of the speaker's voice to extract characteristics of that voice and on an automated comparison of those characteristics to known characteristics of the known person's voice. A speaker segmentation process may be performed on audio of the conversation to produce, for each speaker in the conversation, a segment that includes the audio of that speaker. Audio of each of the segments may then be processed to extract characteristics of that speaker's voice. The characteristics derived from each segment (and thus for multiple speakers) may then be compared to characteristics of the known person's voice to determine whether the speaker for that segment is the known person. For each segment, a degree of match between the voice characteristics of the speaker and the voice characteristics of the known person may be calculated.Type: ApplicationFiled: August 27, 2015Publication date: March 2, 2017Applicant: Nuance Communications, Inc.Inventors: Emanuele Dalmasso, Daniele Colibro, Claudio Vair, Kevin R. Farrell
-
Patent number: 9373330Abstract: A method for performing speaker recognition comprises: estimating respective uncertainties of acoustic coverage of respective speech utterance(s) by first and second speakers, the acoustic coverage representing respective sounds used by the speakers when speaking; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient memory usage by discarding dependencies between uncertainties of different sounds for the speakers; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient computation by representing an inverse of the respective uncertainties of acoustic coverage and then discarding the dependencies between the uncertainties of different sounds for the speakers; and computing a score between the speech utterance(s) by the speakers in a manner that leverages the respective uncertainties of the acoustic coverage during the comparison, the score being indicative of a likelihood that the speakers are the same speaker.Type: GrantFiled: August 7, 2014Date of Patent: June 21, 2016Assignee: Nuance Communications, Inc.Inventors: Sandro Cumani, Claudio Vair, Daniele Ernesto Colibro, Pietro Laface, Kevin R. Farrell
-
Patent number: 9368109Abstract: Reliable speaker-based clustering of speech utterances allows improved speaker recognition and speaker-based speech segmentation. According to at least one example embodiment, an iterative bottom-up speaker-based clustering approach employs voiceprints of speech utterances, such as i-vectors. At each iteration, a clustering confidence score in terms of Silhouette Width Criterion (SWC) values is evaluated, and a pair of nearest clusters is merged into a single cluster. The pair of nearest clusters merged is determined based on a similarity score indicative of similarity between voiceprints associated with different clusters. A final clustering pattern is then determined as a set of clusters associated with an iteration corresponding to the highest clustering confidence score evaluated. The SWC used may further be a modified SWC enabling detection of an early stop of the iterative approach.Type: GrantFiled: May 31, 2013Date of Patent: June 14, 2016Assignee: Nuance Communications, Inc.Inventors: Daniele Ernesto Colibro, Claudio Vair, Kevin R. Farrell
-
Publication number: 20160086607Abstract: Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing.Type: ApplicationFiled: September 18, 2014Publication date: March 24, 2016Inventors: Almog Aley-Raz, Kevin R. Farrell, Oshrit Yaron, Luca Scarpato
-
Publication number: 20160042739Abstract: A method for performing speaker recognition comprises: estimating respective uncertainties of acoustic coverage of respective speech utterance(s) by first and second speakers, the acoustic coverage representing respective sounds used by the speakers when speaking; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient memory usage by discarding dependencies between uncertainties of different sounds for the speakers; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient computation by representing an inverse of the respective uncertainties of acoustic coverage and then discarding the dependencies between the uncertainties of different sounds for the speakers; and computing a score between the speech utterance(s) by the speakers in a manner that leverages the respective uncertainties of the acoustic coverage during the comparison, the score being indicative of a likelihood that the speakers are the same speaker.Type: ApplicationFiled: August 7, 2014Publication date: February 11, 2016Inventors: Sandro Cumani, Claudio Vair, Daniele Ernesto Colibro, Pietro Laface, Kevin R. Farrell
-
Publication number: 20140358541Abstract: Reliable speaker-based clustering of speech utterances allows improved speaker recognition and speaker-based speech segmentation. According to at least one example embodiment, an iterative bottom-up speaker-based clustering approach employs voiceprints of speech utterances, such as i-vectors. At each iteration, a clustering confidence score in terms of Silhouette Width Criterion (SWC) values is evaluated, and a pair of nearest clusters is merged into a single cluster. The pair of nearest clusters merged is determined based on a similarity score indicative of similarity between voiceprints associated with different clusters. A final clustering pattern is then determined as a set of clusters associated with an iteration corresponding to the highest clustering confidence score evaluated. The SWC used may further be a modified SWC enabling detection of an early stop of the iterative approach.Type: ApplicationFiled: May 31, 2013Publication date: December 4, 2014Inventors: Daniele Ernesto Colibro, Claudio Vair, Kevin R. Farrell
-
Publication number: 20140244257Abstract: Typical speaker verification systems usually employ speakers' audio data collected during an enrollment phase when users enroll with the system and provide respective voice samples. Due to technical, business, or other constraints, the enrollment data may not be large enough or rich enough to encompass different inter-speaker and intra-speaker variations. According to at least one embodiment, a method and apparatus employing classifier adaptation based on field data in a deployed voice-based interactive system comprise: collecting representations of voice characteristics, in association with corresponding speakers, the representations being generated by the deployed voice-based interactive system; updating parameters of the classifier, used in speaker recognition, based on the representations collected; and employing the classifier, with the corresponding parameters updated, in performing speaker recognition.Type: ApplicationFiled: February 25, 2013Publication date: August 28, 2014Applicant: NUANCE COMMUNICATIONS, INC.Inventors: Daniele Ernesto Colibro, Claudio Vair, Kevin R. Farrell
-
Publication number: 20140081640Abstract: One aspect includes determining validity of an identity asserted by a speaker using a voice print associated with a user whose identity the speaker is asserting, the voice print obtained from characteristic features of at least one first voice signal obtained from the user uttering at least one enrollment utterance including at least one enrollment word by obtaining a second voice signal of the speaker uttering at least one challenge utterance that includes at least one word not in the at least one enrollment utterance, obtaining at least one characteristic feature from the second voice signal, comparing the at least one characteristic feature with at least a portion of the voice print to determine a similarity between the at least one characteristic feature and the at least a portion of the voice print, and determining whether the speaker is the user based, at least in part, on the similarity.Type: ApplicationFiled: November 21, 2013Publication date: March 20, 2014Applicant: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Patent number: 8620657Abstract: One aspect includes determining validity of an identity asserted by a speaker using a voice print associated with a user whose identity the speaker is asserting, the voice print obtained from characteristic features of at least one first voice signal obtained from the user uttering at least one enrollment utterance including at least one enrollment word by obtaining a second voice signal of the speaker uttering at least one challenge utterance that includes at least one word not in the at least one enrollment utterance, obtaining at least one characteristic feature from the second voice signal, comparing the at least one characteristic feature with at least a portion of the voice print to determine a similarity between the at least one characteristic feature and the at least a portion of the voice print, and determining whether the speaker is the user based, at least in part, on the similarity.Type: GrantFiled: September 14, 2012Date of Patent: December 31, 2013Assignee: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Patent number: 8386263Abstract: In one aspect, a method for determining a validity of an identity asserted by a speaker using a voice print is provided. The method comprises acts of performing a first verification stage comprising comparing a first voice signal from the speaker uttering at least one first challenge utterance with at least a portion of the voice print and performing a second verification stage if it is concluded in the first verification stage that the first voice signal was obtained from an utterance by the user. The second verification stage comprises adapting at least one parameter of the voice print based, at least in part, on the first voice signal to obtain an adapted voice print, and comparing a second voice signal from the speaker uttering at least one second challenge utterance with at least a portion of the adapted voice print.Type: GrantFiled: April 9, 2012Date of Patent: February 26, 2013Assignee: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Publication number: 20130030809Abstract: One aspect includes determining validity of an identity asserted by a speaker using a voice print associated with a user whose identity the speaker is asserting, the voice print obtained from characteristic features of at least one first voice signal obtained from the user uttering at least one enrollment utterance including at least one enrollment word by obtaining a second voice signal of the speaker uttering at least one challenge utterance that includes at least one word not in the at least one enrollment utterance, obtaining at least one characteristic feature from the second voice signal, comparing the at least one characteristic feature with at least a portion of the voice print to determine a similarity between the at least one characteristic feature and the at least a portion of the voice print, and determining whether the speaker is the user based, at least in part, on the similarity.Type: ApplicationFiled: September 14, 2012Publication date: January 31, 2013Applicant: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Patent number: 8332223Abstract: In one aspect, a method for determining validity of an identity asserted by a speaker using a voice print associated with a user whose identity the speaker is asserting, the voice print obtained from characteristic features of at least one first voice signal obtained from the user uttering at least one enrollment utterance including at least one enrollment word is provided.Type: GrantFiled: October 24, 2008Date of Patent: December 11, 2012Assignee: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Publication number: 20120239398Abstract: In one aspect, a method for determining a validity of an identity asserted by a speaker using a voice print is provided. The method comprises acts of performing a first verification stage comprising comparing a first voice signal from the speaker uttering at least one first challenge utterance-with at least a portion of the voice print and performing a second verification stage if it is concluded in the first verification stage that the first voice signal was obtained from an utterance by the user. The second verification stage comprises adapting at least one parameter of the voice print based, at least in part, on the first voice signal to obtain an adapted voice print, and comparing a second voice signal from the speaker uttering at least one second challenge utterance with at least a portion of the adapted voice print.Type: ApplicationFiled: April 9, 2012Publication date: September 20, 2012Applicant: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter
-
Patent number: 8190437Abstract: In one aspect, a method for determining a validity of an identity asserted by a speaker using a voice print is provided. The method comprises acts of performing a first verification stage comprising comparing a first voice signal from the speaker uttering at least one first challenge utterance with at least a portion of the voice print and performing a second verification stage if it is concluded in the first verification stage that the first voice signal was obtained from an utterance by the user. The second verification stage comprises adapting at least one parameter of the voice print based, at least in part, on the first voice signal to obtain an adapted voice print, and comparing a second voice signal from the speaker uttering at least one second challenge utterance with at least a portion of the adapted voice print.Type: GrantFiled: October 24, 2008Date of Patent: May 29, 2012Assignee: Nuance Communications, Inc.Inventors: Kevin R. Farrell, David A. James, William F. Ganong, III, Jerry K. Carter