Patents by Inventor David C. Haws
David C. Haws 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: 11335434Abstract: Various embodiments select markers for modeling epistasis effects. In one embodiment, a processor receives a set of genetic markers and a phenotype. A relevance score is determined with respect to the phenotype for each of the set of genetic markers. A threshold is set based on the relevance score of a genetic marker with a highest relevancy score. A relevance score is determined for at least one genetic marker in the set of genetic markers for at least one interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers. The at least one interaction is added to a top-k feature set based on the relevance score of the at least one interaction satisfying the threshold.Type: GrantFiled: September 14, 2018Date of Patent: May 17, 2022Assignee: International Business Machines CorporationInventors: David C. Haws, Dan He, Laxmi P. Parida
-
Patent number: 11335433Abstract: Various embodiments select markers for modeling epistasis effects. In one embodiment, a processor receives a set of genetic markers and a phenotype. A relevance score is determined with respect to the phenotype for each of the set of genetic markers. A threshold is set based on the relevance score of a genetic marker with a highest relevancy score. A relevance score is determined for at least one genetic marker in the set of genetic markers for at least one interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers. The at least one interaction is added to a top-k feature set based on the relevance score of the at least one interaction satisfying the threshold.Type: GrantFiled: September 14, 2018Date of Patent: May 17, 2022Assignee: International Business Machines CorporationInventors: David C. Haws, Dan He, Laxmi P. Parida
-
Patent number: 10902843Abstract: Audio features, such as perceptual linear prediction (PLP) features and time derivatives thereof, are extracted from frames of training audio data including speech by multiple speakers, and silence, such as by using linear discriminant analysis (LDA). The frames are clustered into k-means clusters using distance measures, such as Mahalanobis distance measures, of means and variances of the extracted audio features of the frames. A recurrent neural network (RNN) is trained on the extracted audio features of the frames and cluster identifiers of the k-means clusters into which the frames have been clustered. The RNN is applied to audio data to segment audio data into segments that each correspond to one of the cluster identifiers. Each segment can be assigned a label corresponding to one of the cluster identifiers. Speech recognition can be performed on the segments.Type: GrantFiled: November 15, 2019Date of Patent: January 26, 2021Assignee: International Business Machines CorporationInventors: Dimitrios B. Dimitriadis, David C. Haws, Michael Picheny, George Saon, Samuel Thomas
-
Publication number: 20200082809Abstract: Audio features, such as perceptual linear prediction (PLP) features and time derivatives thereof, are extracted from frames of training audio data including speech by multiple speakers, and silence, such as by using linear discriminant analysis (LDA). The frames are clustered into k-means clusters using distance measures, such as Mahalanobis distance measures, of means and variances of the extracted audio features of the frames. A recurrent neural network (RNN) is trained on the extracted audio features of the frames and cluster identifiers of the k-means clusters into which the frames have been clustered. The RNN is applied to audio data to segment audio data into segments that each correspond to one of the cluster identifiers. Each segment can be assigned a label corresponding to one of the cluster identifiers. Speech recognition can be performed on the segments.Type: ApplicationFiled: November 15, 2019Publication date: March 12, 2020Inventors: DIMITRIOS B. DIMITRIADIS, David C. Haws, MICHAEL PICHENY, GEORGE SAON, Samuel Thomas
-
Patent number: 10546575Abstract: Audio features, such as perceptual linear prediction (PLP) features and time derivatives thereof, are extracted from frames of training audio data including speech by multiple speakers, and silence, such as by using linear discriminant analysis (LDA). The frames are clustered into k-means clusters using distance measures, such as Mahalanobis distance measures, of means and variances of the extracted audio features of the frames. A recurrent neural network (RNN) is trained on the extracted audio features of the frames and cluster identifiers of the k-means clusters into which the frames have been clustered. The RNN is applied to audio data to segment audio data into segments that each correspond to one of the cluster identifiers. Each segment can be assigned a label corresponding to one of the cluster identifiers. Speech recognition can be performed on the segments.Type: GrantFiled: December 14, 2016Date of Patent: January 28, 2020Assignee: International Business Machines CorporationInventors: Dimitrios B. Dimitriadis, David C. Haws, Michael Picheny, George Saon, Samuel Thomas
-
Patent number: 10249292Abstract: Speaker diarization is performed on audio data including speech by a first speaker, speech by a second speaker, and silence. The speaker diarization includes segmenting the audio data using a long short-term memory (LSTM) recurrent neural network (RNN) to identify change points of the audio data that divide the audio data into segments. The speaker diarization includes assigning a label selected from a group of labels to each segment of the audio data using the LSTM RNN. The group of labels comprising includes labels corresponding to the first speaker, the second speaker, and the silence. Each change point is a transition from one of the first speaker, the second speaker, and the silence to a different one of the first speaker, the second speaker, and the silence. Speech recognition can be performed on the segments that each correspond to one of the first speaker and the second speaker.Type: GrantFiled: December 14, 2016Date of Patent: April 2, 2019Assignee: International Business Machines CorporationInventors: Dimitrios B. Dimitriadis, David C. Haws, Michael Picheny, George Saon, Samuel Thomas
-
Publication number: 20190012426Abstract: Various embodiments select markers for modeling epistasis effects. In one embodiment, a processor receives a set of genetic markers and a phenotype. A relevance score is determined with respect to the phenotype for each of the set of genetic markers. A threshold is set based on the relevance score of a genetic marker with a highest relevancy score. A relevance score is determined for at least one genetic marker in the set of genetic markers for at least one interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers. The at least one interaction is added to a top-k feature set based on the relevance score of the at least one interaction satisfying the threshold.Type: ApplicationFiled: September 14, 2018Publication date: January 10, 2019Inventors: David C. HAWS, Dan HE, Laxmi P. PARIDA
-
Publication number: 20190012427Abstract: Various embodiments select markers for modeling epistasis effects. In one embodiment, a processor receives a set of genetic markers and a phenotype. A relevance score is determined with respect to the phenotype for each of the set of genetic markers. A threshold is set based on the relevance score of a genetic marker with a highest relevancy score. A relevance score is determined for at least one genetic marker in the set of genetic markers for at least one interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers. The at least one interaction is added to a top-k feature set based on the relevance score of the at least one interaction satisfying the threshold.Type: ApplicationFiled: September 14, 2018Publication date: January 10, 2019Applicant: International Business Machines CorporationInventors: David C. HAWS, Dan HE, Laxmi P. PARIDA
-
Publication number: 20180166067Abstract: Audio features, such as perceptual linear prediction (PLP) features and time derivatives thereof, are extracted from frames of training audio data including speech by multiple speakers, and silence, such as by using linear discriminant analysis (LDA). The frames are clustered into k-means clusters using distance measures, such as Mahalanobis distance measures, of means and variances of the extracted audio features of the frames. A recurrent neural network (RNN) is trained on the extracted audio features of the frames and cluster identifiers of the k-means clusters into which the frames have been clustered. The RNN is applied to audio data to segment audio data into segments that each correspond to one of the cluster identifiers. Each segment can be assigned a label corresponding to one of the cluster identifiers. Speech recognition can be performed on the segments.Type: ApplicationFiled: December 14, 2016Publication date: June 14, 2018Inventors: Dimitrios B. Dimitriadis, David C. Haws, Michael Picheny, George Saon, Samuel Thomas
-
Publication number: 20180166066Abstract: Speaker diarization is performed on audio data including speech by a first speaker, speech by a second speaker, and silence. The speaker diarization includes segmenting the audio data using a long short-term memory (LSTM) recurrent neural network (RNN) to identify change points of the audio data that divide the audio data into segments. The speaker diarization includes assigning a label selected from a group of labels to each segment of the audio data using the LSTM RNN. The group of labels comprising includes labels corresponding to the first speaker, the second speaker, and the silence. Each change point is a transition from one of the first speaker, the second speaker, and the silence to a different one of the first speaker, the second speaker, and the silence. Speech recognition can be performed on the segments that each correspond to one of the first speaker and the second speaker.Type: ApplicationFiled: December 14, 2016Publication date: June 14, 2018Inventors: Dimitrios B. Dimitriadis, David C. Haws, Michael Picheny, George Saon, Samuel Thomas
-
Patent number: 9075748Abstract: Various embodiments provide lossless compression of an enumeration space for genetic founder lines. In one embodiment, an input comprising a set of genetic founder lines and a maximum number of generations G is obtained. A set of genetic crossing templates of a height h is generated. A determination is made if at least a first genetic crossing template in the set of genetic crossing templates is redundant with respect to a second genetic crossing template in the set of genetic crossing templates. Based on the at least first genetic crossing template being redundant is redundant with respect to the second genetic crossing template, the at least first genetic crossing template is removed from the set of genetic crossing templates. This process of removing the at least first genetic crossing template from the set of genetic crossing templates the redundant creates an updated set of genetic crossing templates.Type: GrantFiled: October 9, 2013Date of Patent: July 7, 2015Assignee: International Business Machines CorporationInventors: David C. Haws, Laxmi P. Parida
-
Patent number: 9041566Abstract: Various embodiments provide lossless compression of an enumeration space for genetic founder lines. In one embodiment, an input comprising a set of genetic founder lines and a maximum number of generations G is obtained. A set of genetic crossing templates of a height h is generated. A determination is made if at least a first genetic crossing template in the set of genetic crossing templates is redundant with respect to a second genetic crossing template in the set of genetic crossing templates. Based on the at least first genetic crossing template being redundant is redundant with respect to the second genetic crossing template, the at least first genetic crossing template is removed from the set of genetic crossing templates. This process of removing the at least first genetic crossing template from the set of genetic crossing templates the redundant creates an updated set of genetic crossing templates.Type: GrantFiled: August 30, 2013Date of Patent: May 26, 2015Assignee: International Business Machines CorporationInventors: David C. Haws, Laxmi P. Parida
-
Publication number: 20150061903Abstract: Various embodiments provide lossless compression of an enumeration space for genetic founder lines. In one embodiment, an input comprising a set of genetic founder lines and a maximum number of generations G is obtained. A set of genetic crossing templates of a height h is generated. A determination is made if at least a first genetic crossing template in the set of genetic crossing templates is redundant with respect to a second genetic crossing template in the set of genetic crossing templates. Based on the at least first genetic crossing template being redundant is redundant with respect to the second genetic crossing template, the at least first genetic crossing template is removed from the set of genetic crossing templates. This process of removing the at least first genetic crossing template from the set of genetic crossing templates the redundant creates an updated set of genetic crossing templates.Type: ApplicationFiled: August 30, 2013Publication date: March 5, 2015Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David C. HAWS, Laxmi P. PARIDA
-
Publication number: 20150065361Abstract: Various embodiments provide lossless compression of an enumeration space for genetic founder lines. In one embodiment, an input comprising a set of genetic founder lines and a maximum number of generations G is obtained. A set of genetic crossing templates of a height h is generated. A determination is made if at least a first genetic crossing template in the set of genetic crossing templates is redundant with respect to a second genetic crossing template in the set of genetic crossing templates. Based on the at least first genetic crossing template being redundant is redundant with respect to the second genetic crossing template, the at least first genetic crossing template is removed from the set of genetic crossing templates. This process of removing the at least first genetic crossing template from the set of genetic crossing templates the redundant creates an updated set of genetic crossing templates.Type: ApplicationFiled: October 9, 2013Publication date: March 5, 2015Applicant: International Business Machines CorporationInventors: David C. HAWS, Laxmi P. PARIDA
-
Publication number: 20140156235Abstract: Various embodiments generate a quantitative model of genetic effect. In one embodiment, a processor receives a set of loci of an entity. Each locus is associated with a contribution value to a given physical trait. A first set of interacting loci associated with a first interaction and at least a second set of interacting loci associated with at least a second interaction are identified. The first interaction type is associated with a first interaction model. The at least the second interaction is associated at least a second interaction model. A model of a quantitative value of the entity is generated based on at least the contribution value associated with each locus in the set of loci, a contribution value of the first interaction as defined by the first interaction model, and a contribution value of the second interaction as defined by the at least the second interaction model.Type: ApplicationFiled: December 5, 2012Publication date: June 5, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David C. Haws, Dan He, Laxmi P. Parida
-
Publication number: 20140156236Abstract: Various embodiments generate a quantitative model of genetic effect. In one embodiment, a processor receives a set of loci of an entity. Each locus is associated with a contribution value to a given physical trait. A first set of interacting loci associated with a first interaction and at least a second set of interacting loci associated with at least a second interaction are identified. The first interaction type is associated with a first interaction model. The at least the second interaction is associated at least a second interaction model. A model of a quantitative value of the entity is generated based on at least the contribution value associated with each locus in the set of loci, a contribution value of the first interaction as defined by the first interaction model, and a contribution value of the second interaction as defined by the at least the second interaction model.Type: ApplicationFiled: September 18, 2013Publication date: June 5, 2014Applicant: International Business Machines CorporationInventors: David C. HAWS, Dan HE, Laxmi P. PARIDA