Patents by Inventor Hong-Kwang Jeff Kuo
Hong-Kwang Jeff Kuo 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: 11929062Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.Type: GrantFiled: September 15, 2020Date of Patent: March 12, 2024Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Hong-Kwang Jeff Kuo, Zoltan Tueske, Samuel Thomas, Yinghui Huang, Brian E. D. Kingsbury, Kartik Audhkhasi
-
Patent number: 11587551Abstract: An illustrative embodiment includes a method for training an end-to-end (E2E) spoken language understanding (SLU) system. The method includes receiving a training corpus comprising a set of text classified using one or more sets of semantic labels but unpaired with speech and using the set of unpaired text to train the E2E SLU system to classify speech using at least one of the one or more sets of semantic labels. The method may include training a text-to-intent model using the set of unpaired text; and training a speech-to-intent model using the text-to-intent model. Alternatively or additionally, the method may include using a text-to-speech (TTS) system to generate synthetic speech from the unpaired text; and training the E2E SLU system using the synthetic speech.Type: GrantFiled: April 7, 2020Date of Patent: February 21, 2023Assignee: International Business Machines CorporationInventors: Hong-Kwang Jeff Kuo, Yinghui Huang, Samuel Thomas, Kartik Audhkhasi, Michael Alan Picheny
-
Publication number: 20220084508Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.Type: ApplicationFiled: September 15, 2020Publication date: March 17, 2022Inventors: Hong-Kwang Jeff Kuo, Zoltan Tueske, Samuel Thomas, Yinghui Huang, Brian E. D. Kingsbury, Kartik Audhkhasi
-
Publication number: 20210312906Abstract: An illustrative embodiment includes a method for training an end-to-end (E2E) spoken language understanding (SLU) system. The method includes receiving a training corpus comprising a set of text classified using one or more sets of semantic labels but unpaired with speech and using the set of unpaired text to train the E2E SLU system to classify speech using at least one of the one or more sets of semantic labels. The method may include training a text-to-intent model using the set of unpaired text; and training a speech-to-intent model using the text-to-intent model. Alternatively or additionally, the method may include using a text-to-speech (TTS) system to generate synthetic speech from the unpaired text; and training the E2E SLU system using the synthetic speech.Type: ApplicationFiled: April 7, 2020Publication date: October 7, 2021Inventors: Hong-Kwang Jeff Kuo, Yinghui Huang, Samuel Thomas, Kartik Audhkhasi, Michael Alan Picheny
-
Patent number: 9477753Abstract: Systems and methods for processing a query include determining a plurality of sets of match candidates for a query using a processor, each of the plurality of sets of match candidates being independently determined from a plurality of diverse word lattice generation components of different type. The plurality of sets of match candidates is merged by generating a first score for each match candidate to provide a merged set of match candidates. A second score is computed for each match candidate of the merged set based upon features of that match candidate. The first score and the second score are combined to provide a final set of match candidates as matches to the query.Type: GrantFiled: March 12, 2013Date of Patent: October 25, 2016Assignee: International Business Machines CorporationInventors: Brian E. D. Kingsbury, Hong-Kwang Jeff Kuo, Lidia Luminita Mangu, Hagen Soltau
-
Publication number: 20140278390Abstract: Systems and methods for processing a query include determining a plurality of sets of match candidates for a query using a processor, each of the plurality of sets of match candidates being independently determined from a plurality of diverse word lattice generation components of different type. The plurality of sets of match candidates is merged by generating a first score for each match candidate to provide a merged set of match candidates. A second score is computed for each match candidate of the merged set based upon features of that match candidate. The first score and the second score are combined to provide a final set of match candidates as matches to the query.Type: ApplicationFiled: March 12, 2013Publication date: September 18, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Brian E. D. Kingsbury, Hong-Kwang Jeff Kuo, Lidia Luminita Mangu, Hagen Soltau
-
Patent number: 8768699Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.Type: GrantFiled: April 15, 2010Date of Patent: July 1, 2014Assignee: International Business Machines CorporationInventors: Yuqing Gao, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Patent number: 8509396Abstract: A call routing system is created by receiving a set of initial target classes and a corresponding set of topic descriptions. Non-overlapping semantic tokens in the set of topic descriptions are identified. A set of clear target classes from the non-overlapping semantic tokens and the initial target classes is identified. Overlapping semantic tokens from the set of topic descriptions are identified. A set of vague classes is identified from the overlapping semantic tokens and the initial target classes. A set of disambiguation dialogues and a set of grammar prompts is generated according to the overlapping and non-overlapping semantic tokens. The call routing system is then created based on the set of clear target classes, the set of vague target classes, and the set of disambiguation dialogues.Type: GrantFiled: September 24, 2009Date of Patent: August 13, 2013Assignee: International Business Machines CorporationInventors: Ea-Ee Jan, Hong-Kwang Jeff Kuo, David M. Lubensky
-
Patent number: 8379806Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.Type: GrantFiled: August 22, 2008Date of Patent: February 19, 2013Assignee: International Business Machines CorporationInventors: Cheng Wu, Andrzej Sakrajda, Hong-Kwang Jeff Kuo, Vaibhava Goel, David Lubensky
-
Publication number: 20110069822Abstract: A call routing system is created by receiving a set of initial target classes and a corresponding set of topic descriptions. Non-overlapping semantic tokens in the set of topic descriptions are identified. A set of clear target classes from the non-overlapping semantic tokens and the initial target classes is identified. Overlapping semantic tokens from the set of topic descriptions are identified. A set of vague classes is identified from the overlapping semantic tokens and the initial target classes. A set of disambiguation dialogues and a set of grammar prompts is generated according to the overlapping and non-overlapping semantic tokens. The call routing system is then created based on the set of clear target classes, the set of vague target classes, and the set of disambiguation dialogues.Type: ApplicationFiled: September 24, 2009Publication date: March 24, 2011Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ea-Ee Jan, Hong-Kwang Jeff Kuo, David M. Lubensky
-
Patent number: 7860705Abstract: A technique for context adaptation of a speech-to-speech translation system is provided. A plurality of sets of paralinguistic attribute values is obtained from a plurality of input signals. Each set of the plurality of sets of paralinguistic attribute values is extracted from a corresponding input signal of the plurality of input signals via a corresponding classifier of a plurality of classifiers. A final set of paralinguistic attribute values is generated for the plurality of input signals from the plurality of sets of paralinguistic attribute values. Performance of at least one of a speech recognition module, a translation module and a text-to-speech module of the speech-to-speech translation system is modified in accordance with the final set of paralinguistic attribute values for the plurality of input signals.Type: GrantFiled: September 1, 2006Date of Patent: December 28, 2010Assignee: International Business Machines CorporationInventors: Mohamed A. Afify, Yuqing Gao, Liang Gu, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Publication number: 20100204978Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.Type: ApplicationFiled: April 15, 2010Publication date: August 12, 2010Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Yuqing Gao, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Patent number: 7734467Abstract: Techniques for assisting in translation are provided A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.Type: GrantFiled: May 22, 2008Date of Patent: June 8, 2010Assignee: International Business Machines CorporationInventors: Yuqing Gao, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Patent number: 7552053Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.Type: GrantFiled: August 22, 2005Date of Patent: June 23, 2009Assignee: International Business Machines CorporationInventors: Yuqing Gao, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Publication number: 20080310603Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.Type: ApplicationFiled: August 22, 2008Publication date: December 18, 2008Inventors: Cheng Wu, Andrzej Sakrajda, Hong-Kwang Jeff Kuo, Vaibhava Goel, David Lubensky
-
Patent number: 7453992Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.Type: GrantFiled: April 14, 2005Date of Patent: November 18, 2008Assignee: International Business Machines CorporationInventors: Cheng Wu, Andrzej Sakrajda, Hong-Kwang Jeff Kuo, Vaibhava Goel, David Lubensky
-
Publication number: 20080228484Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.Type: ApplicationFiled: May 22, 2008Publication date: September 18, 2008Applicant: International Business Machines CorporationInventors: Yuqing Gao, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Publication number: 20080059147Abstract: A technique for context adaptation of a speech-to-speech translation system is provided. A plurality of sets of paralinguistic attribute values is obtained from a plurality of input signals. Each set of the plurality of sets of paralinguistic attribute values is extracted from a corresponding input signal of the plurality of input signals via a corresponding classifier of a plurality of classifiers. A final set of paralinguistic attribute values is generated for the plurality of input signals from the plurality of sets of paralinguistic attribute values. Performance of at least one of a speech recognition module, a translation module and a text-to-speech module of the speech-to-speech translation system is modified in accordance with the final set of paralinguistic attribute values for the plurality of input signals.Type: ApplicationFiled: September 1, 2006Publication date: March 6, 2008Applicant: International Business Machines CorporationInventors: Mohamed A. Afify, Yuqing Gao, Liang Gu, Hong-Kwang Jeff Kuo, Bowen Zhou
-
Patent number: 6925432Abstract: A method and apparatus for performing discriminative training of, for example, call routing training data (or, alternatively, other classification training data) which improves the subsequent classification of a user's natural language based requests. An initial scoring matrix is generated based on the training data and then the scoring matrix is adjusted so as to improve the discrimination between competing classes (e.g., destinations). In accordance with one illustrative embodiment of the present invention a Generalized Probabilistic Descent (GPD) algorithm may be advantageously employed to provide the improved discrimination.Type: GrantFiled: December 26, 2000Date of Patent: August 2, 2005Assignee: Lucent Technologies Inc.Inventors: Chin-Hui Lee, Hong-Kwang Jeff Kuo
-
Publication number: 20020116174Abstract: A method and apparatus for performing discriminative training of, for example, call routing training data (or, alternatively, other classification training data) which improves the subsequent classification of a user's natural language based requests. An initial scoring matrix is generated based on the training data and then the scoring matrix is adjusted so as to improve the discrimination between competing classes (e.g., destinations). In accordance with one illustrative embodiment of the present invention a Generalized Probabilistic Descent (GPD) algorithm may be advantageously employed to provide the improved discrimination.Type: ApplicationFiled: December 26, 2000Publication date: August 22, 2002Inventors: Chin-Hui Lee, Hong-Kwang Jeff Kuo