专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20170206875A1 COGNITIVE MUSIC ENGINE USING UNSUPERVISED LEARNING 审中-公开
公开(公告)号：US20170206875A1
公开(公告)日：2017-07-20
申请号：US15473543
申请日：2017-03-29
申请人： International Business Machines Corporation
发明人： Inseok Hwang , Jente B Kuang , Janani Mukundan
IPC分类号： G10H1/00 , G06N5/04
CPC分类号： G10H1/0025 , G06N3/0472 , G06N3/088 , G06N5/04 , G10H2210/081 , G10H2210/111 , G10H2210/115 , G10H2210/125 , G10H2210/131 , G10H2210/565 , G10H2220/101 , G10H2240/085 , G10H2250/311
摘要： A method for generating a musical composition based on user input is described. A first set of musical characteristics from a first input musical piece is received as an input vector. The first set of musical characteristics is perturbed to create a perturbed input vector as input in a first set of nodes in a first visible layer of an unsupervised neural net. The unsupervised neural net comprised of a plurality of computing layers, each computing layer composed of a respective set of nodes. The unsupervised neural net is operated to calculate an output vector from a higher level hidden layer in the unsupervised neural net. The output vector is used to create an output musical piece.

72. 发明授权

US09326082B2 Song transition effects for browsing 有权
标题翻译：歌曲过渡效果浏览
公开(公告)号：US09326082B2
公开(公告)日：2016-04-26
申请号：US13995780
申请日：2011-12-15
申请人： Jonas Engdegard
发明人： Jonas Engdegard
IPC分类号： H04H60/04 , G11B27/34 , G11B27/028 , H04S1/00 , G10H1/00 , G11B27/038 , H04S7/00
CPC分类号： H04S1/00 , G10H1/0008 , G10H2210/125 , G10H2210/131 , G10H2210/136 , G11B27/038 , H04H60/04 , H04S7/30 , H04S2400/11
摘要： In one aspect, a method of providing directive transitions between audio signals comprises associating a first/second browsing direction (A1, A2) with a first/second transition effect template. In response to a browsing action in one of said browsing directions, a transition is played in which an exit segment (S0-out1, S0-out2) and an entry segment (S1-in, S2-in) are mixed in accordance with the associated transition effect template. A further aspect proposes a method of transitioning between audio signals decoded from audio data including time markers encoded as audio metadata and indicating at least one section of the respective audio signal. The method includes retrieving time marking information in the audio data; extracting an exit segment (S0-out1, S0-out2) and an entry segment (S1-in, S2-in), wherein an endpoint of at least one of the segments is synchronized with a time marker; and playing a transition in which the exit and entry segments are mixed in accordance with a transition effect template.
摘要翻译：一方面，提供音频信号之间的指示转换的方法包括将第一/第二浏览方向（A1，A2）与第一/第二过渡效果模板相关联。响应于所述浏览方向之一中的浏览动作，根据所述浏览方向进行转换，其中退出段（S0-out1，S0-out2）和入口段（S1-in，S2-in）关联过渡效应模板。另一方面提出了一种在音频数据解码的音频信号之间进行转换的方法，包括被编码为音频元数据并指示相应音频信号的至少一个部分的时间标记。该方法包括：在音频数据中检索时间标记信息; 提取出口段（S0-out1，S0-out2）和入口段（S1-in，S2-in），其中至少一个段的端点与时间标记同步; 并且根据转换效果模板播放出口和进入段被混合的转换。

73. 发明授权

US09286877B1 Method and apparatus for computer-aided variation of music and other sequences, including variation by chaotic mapping 有权
标题翻译：音乐等序列的计算机辅助变化的方法和装置，包括混沌映射的变化
公开(公告)号：US09286877B1
公开(公告)日：2016-03-15
申请号：US14264612
申请日：2014-04-29
申请人： Diana Dabby
发明人： Diana Dabby
IPC分类号： A63H5/00 , G04B13/00 , G10H7/00 , B42D15/02
CPC分类号： B42D15/022 , G10H1/0025 , G10H1/0066 , G10H2210/115 , G10H2210/131 , G10H2210/151 , G10H2240/071 , G10H2250/211
摘要： An altered but recognizable variant of an input musical composition is created by parsing the input into elements, selecting elements for replacement using a hole-selecting algorithm, and replacing the selected elements using a substitution algorithm. A plurality of tracks from the same composition, or from different compositions, can be separately varied and combined, or concatenated and varied together, or used as a seed source of a substitution algorithm, to create a remix or mash-up. Music variants can be combined with photographs, images, or videos, for distribution to recipients, or for a project presentation or story board. Greeting cards, MP3 players, mobile electronic devices, wearable electronic devices, toys, video games, websites, and ringtones can be configured to create and play a new variant of an input composition each time it is accessed. Websites can be used to host and track successive, “chain” variations of an input musical composition.
摘要翻译：通过将输入解析为元素，使用空穴选择算法选择用于替换的元素，以及使用替换算法替换所选择的元素来创建输入音乐作品的改变但可识别的变体。来自相同组合物或来自不同组合物的多个轨道可以分别变化并组合，或连接和变化在一起，或用作替代算法的种子源，以产生混合或混搭。音乐变体可以与照片，图像或视频相结合，分发给收件人，或者用于项目演示或故事板。贺卡，MP3播放器，移动电子设备，可穿戴电子设备，玩具，视频游戏，网站和铃声可以被配置为在每次访问时创建和播放输入作品的新变体。网站可以用于主持和跟踪输入音乐作品的连续“链”变体。

74. 发明申请

US20150255052A1 GENERATIVE SCHEDULING METHOD 有权
标题翻译：一般调度方法
公开(公告)号：US20150255052A1
公开(公告)日：2015-09-10
申请号：US14438721
申请日：2013-10-30
申请人： JUKEDECK LTD.
发明人： Edmund Rex
IPC分类号： G10H1/00
CPC分类号： G10H1/0066 , G10H1/0025 , G10H1/40 , G10H2210/121 , G10H2210/131 , G10H2250/015
摘要： A method for providing one or more outputs at one or more respective time instants is provided. The method comprises generating a data object executable to provide an output, placing the object in a position in a sequence, and executing the object at said position in said sequence to provide said output. Each position in the sequence represents a time instant.
摘要翻译：提供一种在一个或多个相应的时刻提供一个或多个输出的方法。该方法包括生成可执行以提供输出的数据对象，将对象放置在序列中的位置，以及在所述序列中的所述位置处执行对象以提供所述输出。序列中的每个位置代表一个时刻。

75. 发明申请

US20140270181A1 DJ Stem Systems And Methods 有权
标题翻译： DJ干系统与方法
公开(公告)号：US20140270181A1
公开(公告)日：2014-09-18
申请号：US13802548
申请日：2013-03-13
申请人： BEATPORT, LLC
发明人： Michael Peter Siciliano
IPC分类号： H04S1/00
CPC分类号： G10H1/0008 , G10H2210/061 , G10H2210/125 , G10H2210/131 , G10H2210/295 , G11B27/005 , G11B27/036 , G11B27/038 , G11B27/105 , G11B27/32 , H04H60/04 , H04R29/008 , H04S1/00 , H04S1/007 , H04S7/00
摘要： Systems and methods selectively mix a first and second song together during a live performance. The first song has a plurality of first stems, each having stereo audio that combine to form the audio of the first song. The second song has a plurality of second stems, each having stereo audio that combine to form the audio of the second song. A computer, with memory and a processor, executes machine readable instructions of a multiple channel audio mixing application with stored within the memory. The multiple channel audio mixing application plays and mixes audio of at least one of the first stems with audio of at least one of the second stems. The multiple channel audio mixing application is controlled in real-time during the performance to select the at least one first stem and the at least one second stem for the mixing.
摘要翻译：系统和方法在现场表演期间选择性地混合第一和第二首歌曲。第一首歌曲具有多个第一声部，每个声部具有组合以形成第一首歌曲的音频的立体声音频。第二首歌曲具有多个第二声部，每个声部具有组合以形成第二首歌曲的音频的立体声音频。具有存储器和处理器的计算机执行存储在存储器内的多通道音频混合应用的机器可读指令。多声道音频混合应用播放并混合至少一个第一音杆的音频与至少一个第二音柄的音频。多声道音频混合应用在性能期间被实时控制以选择用于混合的至少一个第一杆和至少一个第二杆。

76. 发明申请

US20120222540A1 GENERATING TONES BY COMBINING SOUND MATERIALS 有权
标题翻译：通过组合声音材料产生音调
公开(公告)号：US20120222540A1
公开(公告)日：2012-09-06
申请号：US13411188
申请日：2012-03-02
申请人： Jun Usui , Taishi Kamiya
发明人： Jun Usui , Taishi Kamiya
IPC分类号： G10H1/06
CPC分类号： G10H1/0025 , G10H2210/125 , G10H2210/131 , G10H2220/106 , G10H2240/145 , G10H2240/305
摘要： The apparatus displays, on a display screen, an icon placement region having a time axis defined therein, and displays, in accordance with an input instruction, an icon image with which feature amount information of material data indicative of a sound material is associated. The apparatus further sets a type of a feature amount database, where material data and feature amount information of the material data are associated with each other, along the time axis in accordance with an input instruction. Then, the apparatus references the feature amount database of a type having correspondence relationship in time axis with an icon image to identify material data similar to the feature amount information corresponding to the icon image, and audibly generates a sound at timing corresponding to a position, on the time axis, of the icon image and with content corresponding to the identified material data.
摘要翻译：该装置在显示屏幕上显示其中定义有时间轴的图标放置区域，并且根据输入指令显示与声音材料指示的材料数据的特征量信息相关联的图标图像。该装置还根据输入指令，沿着时间轴设定特征量数据库的种类，其中材料数据的材料数据和特征量信息彼此相关联。然后，该装置将具有时间轴对应关系的类型的特征量数据库与图标图像引用，以识别与图标图像相对应的特征量信息类似的素材数据，并且在与位置对应的定时可听觉地产生声音，在时间轴上，图标图像和与所识别的材料数据相对应的内容。

77. 发明申请

US20120093343A1 ELECTRONICALLY-SIMULATED LIVE MUSIC 失效
标题翻译：电子模拟现场音乐
公开(公告)号：US20120093343A1
公开(公告)日：2012-04-19
申请号：US12906647
申请日：2010-10-18
申请人： James Batchelder , J. Samuel Batchelder
发明人： James Batchelder , J. Samuel Batchelder
IPC分类号： H04B1/00
CPC分类号： G11B27/034 , G10H1/0025 , G10H2210/131 , G10H2250/251
摘要： A method for producing an electronically-simulated live musical performance, the method comprising providing morph-friendly solo tracks, morphing the morph-friendly solo tracks to produce a morphed track, and post-processing the morphed track. The method may also include combining the post-processed morphed track with one or more supporting tracks to produce an acoustic image for playback.
摘要翻译：一种用于制作电子仿真的现场音乐表演的方法，该方法包括提供易变形的独奏曲目，使变形的独奏曲目变形以产生变形的曲目，以及后处理变形曲目。该方法还可以包括将后处理的变形轨迹与一个或多个支撑轨道组合以产生用于回放的声学图像。

78. 发明申请

US20100325163A1 MORPHED MUSICAL PIECE GENERATION SYSTEM AND MORPHED MUSICAL PIECE GENERATION PROGRAM 有权
标题翻译： MORPHED音乐片段生成系统和MORPHED音乐片段生成程序
公开(公告)号：US20100325163A1
公开(公告)日：2010-12-23
申请号：US12866146
申请日：2009-02-04
申请人： Masatoshi Hamanaka
发明人： Masatoshi Hamanaka
IPC分类号： G06F17/30
CPC分类号： G10H1/0025 , G10H2210/131 , G10H2240/131
摘要： A morphed musical piece generation system that enables even a user with little knowledge of music to easily generate a morphed musical piece between two different musical pieces is provided. A first intermediate time-span tree data generation section 6 selectively removes difference information between common time-span tree data and first time-span tree data from the first time-span tree data.Also, a second intermediate time-span tree data generation section 7 performs the same operation to obtain second intermediate time-span tree data. A data combining section combines the first intermediate time-span tree data and the second intermediate time-span tree data to generate combined time-span tree data. A musical piece data generation section generates a morphed musical piece on the basis of the combined time-span tree data.
摘要翻译：提供了一种变形的音乐作品生成系统，其使得即使是具有很少音乐知识的用户也可以容易地在两个不同的乐曲之间产生变形的乐曲。第一中间时间范围树数据生成部分6从第一时间范围树数据中选择性地去除公共时间范围树数据和第一时间范围树数据之间的差分信息。此外，第二中间时间范围树数据生成部7执行相同的操作以获得第二中间时间范围树数据。数据组合部分组合第一中间时间范围树数据和第二中间时间范围树数据以生成组合的时间范围树数据。乐曲数据生成部根据组合的时间范围树数据生成变形乐曲。

79. 发明公开

KR1020100107497A 모핑 악곡 생성장치 및 모핑 악곡생성용 프로그램 有权
标题翻译： MORPHING音乐生成设备和MORPHING音乐生成程序
公开(公告)号：KR1020100107497A
公开(公告)日：2010-10-05
申请号：KR1020107017478
申请日：2009-02-04
申请人： 고쿠리츠켄큐카이하츠호진 카가쿠기쥬츠신코키코
发明人： 하마나카마사토시
IPC分类号： G10K15/04 , G10K15/00
CPC分类号： G10H1/0025 , G10H2210/131 , G10H2240/131
摘要： 본 발명은 음악지식이 부족한 유저에 있어서도 2개가 다른 악곡의 중간적인 모핑(morphing) 악곡을 간단하게 생성할 수 있는 모핑(morphing) 악곡생성장치 및 모핑(morphing) 악곡 생성용 프로그램을 제공하는 것이다.
본 발명에 의한 제1의 중간 타임스팬목 데이터생성부(6)는, 공통 타임스팬목 데이터와 제1의 타임스팬목 데이터의 비공통부분을 제1의 타임스팬목부터 선택적으로 제거한다. 제2의 중간 타임스팬목 데이터생성부(7)도 동일하게 작업을 하고 제2의 중간 타임스팬목 데이터를 생성한다. 악곡데이터 생성부는 통합 타임스팬목 데이터에 의해 모핑(morphing) 악곡을 생성한다.

80. 发明公开

KR1020070054801A 음악 내용 자동 요약 방법 및 그 장치 有权
标题翻译：如何自动总结音乐内容及其设备
公开(公告)号：KR1020070054801A
公开(公告)日：2007-05-30
申请号：KR1020050112763
申请日：2005-11-24
申请人： 삼성전자주식회사
发明人： 김형국 , 김지연 , 엄기완
IPC分类号： G06Q50/10 , G10H1/00
CPC分类号： G10H1/0025 , G10H2210/076 , G10H2210/081 , G10H2210/131 , G06Q50/10
摘要： Embodiments of the present invention relate to a method, medium, and system for summarizing music. The method includes summarizing a music content by extracting an audio feature value from a compressed segment of music data, tracking change points of the music content using the extracted audio feature value and re-configuring segments, selecting a fixed length fragment from each of the reconfigured segments and clustering the selected fragment so as to measure similarity and redundancy between the respective segments, and generating a summary of the music content using a segment selected based on the measured similarity and redundancy between the respective segments.
摘要翻译：在数字内容管理系统中自动总结音乐内容的方法和装置技术领域本发明涉及一种在数字内容管理系统中自动总结音乐内容的方法和装置。该方法包括以下步骤：从音乐数据的压缩区域中提取音频特征值，通过使用所提取的特征值来跟踪音乐内容改变点来重建分段，通过对片段的长度进行聚类来测量每个片段之间的相似性和可重复性，并且使用通过测量的片段之间的相似性和可重复性所选择的片段来生成音乐内容概要并自动总结音乐内容。根据本发明，可以提供一种用于提取压缩区域中的音频特性以提高音乐汇总速度的自动音乐内容汇总方法和装置。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式