Patents by Inventor Dean Schaffer
Dean Schaffer 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: 11900904Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: GrantFiled: February 14, 2022Date of Patent: February 13, 2024Assignee: Smule, Inc.Inventors: Stefan Sullivan, John Shimmin, Dean Schaffer, Perry R. Cook
-
Publication number: 20230005463Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: ApplicationFiled: February 14, 2022Publication date: January 5, 2023Inventors: Stefan SULLIVAN, John SHIMMIN, Dean SCHAFFER, Perry R. COOK
-
Patent number: 11250826Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: GrantFiled: October 28, 2019Date of Patent: February 15, 2022Assignee: Smule, Inc.Inventors: Stefan Sullivan, John Shimmin, Dean Schaffer, Perry R. Cook
-
Publication number: 20200312290Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: ApplicationFiled: October 28, 2019Publication date: October 1, 2020Inventors: Stefan Sullivan, John Shimmin, Dean Schaffer, Perry R. Cook
-
Patent number: 10460711Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: GrantFiled: July 13, 2017Date of Patent: October 29, 2019Assignee: Smule, Inc.Inventors: Stefan Sullivan, John Shimmin, Dean Schaffer, Perry R. Cook
-
Patent number: 10339906Abstract: Advanced, but user-friendly composition and editing environments for musical scores may be provided using the types, and in some cases the instances, of computing devices that will in turn consume musical score content so generated. Indeed, by integrating musical composition facilities within synthetic musical instruments that can be widely deployed on hand-held or portable computing devices, a social music network that includes such synthetic musical instruments gains access to a large, and potentially prolific, population of authors, editors and reviewers, as well as to the community-sourced musical scores that they can generate. By curating such content and/or by applying crowd-sourcing or other computational techniques to maintain quality, a social music network may rapidly deploy the new and ever evolving content that its user community desires.Type: GrantFiled: August 2, 2017Date of Patent: July 2, 2019Assignee: Smule, Inc.Inventors: Charles Espeleta, Jeannie Yang, Perry R. Cook, Oscar Corral, Jonathan Moody, Ran Xie, Jeffrey C. Smith, Dean Schaffer
-
Publication number: 20180151161Abstract: Advanced, but user-friendly composition and editing environments for musical scores may be provided using the types, and in some cases the instances, of computing devices that will in turn consume musical score content so generated. Indeed, by integrating musical composition facilities within synthetic musical instruments that can be widely deployed on hand-held or portable computing devices, a social music network that includes such synthetic musical instruments gains access to a large, and potentially prolific, population of authors, editors and reviewers, as well as to the community-sourced musical scores that they can generate. By curating such content and/or by applying crowd-sourcing or other computational techniques to maintain quality, a social music network may rapidly deploy the new and ever evolving content that its user community desires.Type: ApplicationFiled: August 2, 2017Publication date: May 31, 2018Inventors: Charles Espeleta, Jeannie Yang, Perry R. Cook, Oscar Corral, Jonathan Moody, Ran Xie, Jeffrey C. Smith, Dean Schaffer
-
Publication number: 20180018949Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.Type: ApplicationFiled: July 13, 2017Publication date: January 18, 2018Inventors: Stefan Sullivan, John Shimmin, Dean Schaffer, Perry R. Cook
-
Patent number: 6340601Abstract: A method of reworking copper metallurgy on semiconductor devices which includes selective removal of insulator, selective removal of copper, non-selective removal of copper and insulator followed by the redeposition of an insulating copper barrier layer and at least one metallurgical interconnect layer.Type: GrantFiled: December 30, 1999Date of Patent: January 22, 2002Assignee: International Business Machines CorporationInventors: Thomas F. Curran, Jr., Timothy C. Krywanczyk, Michael S. Lube, Matthew D. Moon, Rock Nadeau, Clark D. Reynolds, Dean A. Schaffer, Joel M. Sharrow, Paul H. Smith, Jr., David C. Thomas, Eric J. White, Kenneth H. Yao