-
公开(公告)号：US20170300567A1
公开(公告)日：2017-10-19
申请号：US15469060
申请日：2017-03-24
申请人： Spotify AB
发明人： Tristan Jehan , Rachel Bittner , Nicola Montecchio , Hunter McCurry , Minwei Gu , Gandalf Hernandez
CPC分类号： G11B27/038 , G06F3/165 , G06F16/4387 , G06F16/635 , G06F16/639 , G06F16/683 , G10H1/0033 , G10H1/42 , G10H2210/00 , G10H2210/571 , G10H2220/321 , G10H2220/395 , G10H2240/075 , G10H2240/131 , G11B27/102 , G11B27/28 , H04L65/4084 , H04L67/22
摘要： A media content item sequencing system determines a sequence for playback of selected media content items, such as media content items in a playlist. The system calculates similarities between all possible pairs of the media content items and determines a sequence of the media content items using the similarities. The sequence of media content items can be determined by modeling the track features of the media content items with a graphic traversal problem and calculating a solution to the problem with various methods.
-
公开(公告)号：US09218728B2
公开(公告)日：2015-12-22
申请号：US13364862
申请日：2012-02-02
申请人： Brady R. Bickel , Robert J. Cole , Megan J. Roberts , Bryan D. Glick , Jason A. Staph , David C. James , Gabriel D. Comi , Stephen Schadler
发明人： Brady R. Bickel , Robert J. Cole , Megan J. Roberts , Bryan D. Glick , Jason A. Staph , David C. James , Gabriel D. Comi , Stephen Schadler
CPC分类号： G08B13/1672 , G01S5/20 , G01S5/22 , G10H2210/00 , G10H2210/041 , H04R3/00 , H04R2410/00 , H04R2499/11
摘要： Methods and apparatus to identify a type of acoustic event Mel Frequency Cepstral Coefficients (MFCCs). In one embodiment, received sound is processed using the MFCCs to locate a peak for comparison with a stored event to determine if the peak corresponds to the acoustic event.
摘要翻译： 识别声学类型的方法和装置Mel频率倒谱系数（MFCC）。 在一个实施例中，使用MFCC来处理接收到的声音以定位用于与存储的事件进行比较的峰值，以确定峰值是否对应于声学事件。
-
公开(公告)号：US09536508B2
公开(公告)日：2017-01-03
申请号：US14691094
申请日：2015-04-20
申请人： Yamaha Corporation
CPC分类号： G10H1/38 , G10H1/00 , G10H1/02 , G10H1/28 , G10H7/02 , G10H2210/00 , G10H2210/576 , G10H2240/145 , G10H2250/541
摘要： An accompaniment data generating apparatus has a storing portion 15 for storing sets of phrase waveform data each related to a chord identified on the basis of a combination of chord type and chord root, and a CPU 9. The CPU 9 carries out a chord information obtaining process for obtaining chord information by which a chord type and a chord root are identified, and a chord note waveform data generating process for generating phrase waveform data indicative of chord notes of the chord root and the chord type identified by the obtained chord information in accordance with the obtained chord information by use of the sets of phrase waveform data stored in the storing portion 15, and outputting the generated data as accompaniment data.
摘要翻译： 伴奏数据生成装置具有存储部15，用于存储与基于和弦类型和弦根的组合识别的和弦相关的短语波形数据组和CPU 9. CPU 9执行和弦信息获取 用于获得用于获得和弦类型和和弦根的所述和弦信息的处理，以及用于产生表示和弦根的和弦音符的短语波形数据的和弦音符数据生成处理和由所获得的和弦信息所识别的和弦类型 通过使用存储在存储部分15中的短语波形数据组获得的和弦信息，并将所生成的数据作为伴奏数据输出。
-
公开(公告)号：US20150228260A1
公开(公告)日：2015-08-13
申请号：US14691094
申请日：2015-04-20
申请人： YAMAHA CORPORATION
IPC分类号： G10H1/02
CPC分类号： G10H1/38 , G10H1/00 , G10H1/02 , G10H1/28 , G10H7/02 , G10H2210/00 , G10H2210/576 , G10H2240/145 , G10H2250/541
摘要： An accompaniment data generating apparatus has a storing portion 15 for storing sets of phrase waveform data each related to a chord identified on the basis of a combination of chord type and chord root, and a CPU 9. The CPU 9 carries out a chord information obtaining process for obtaining chord information by which a chord type and a chord root are identified, and a chord note waveform data generating process for generating phrase waveform data indicative of chord notes of the chord root and the chord type identified by the obtained chord information in accordance with the obtained chord information by use of the sets of phrase waveform data stored in the storing portion 15, and outputting the generated data as accompaniment data.
摘要翻译： 伴奏数据生成装置具有存储部15，用于存储与基于和弦类型和弦根的组合识别的和弦相关的短语波形数据组和CPU 9. CPU 9执行和弦信息获取 用于获得用于获得和弦类型和和弦根的所述和弦信息的处理，以及用于产生表示和弦根的和弦音符的短语波形数据的和弦音符数据生成处理和由所获得的和弦信息所识别的和弦类型 通过使用存储在存储部分15中的短语波形数据组获得的和弦信息，并将所生成的数据作为伴奏数据输出。
-
公开(公告)号：US07812239B2
公开(公告)日：2010-10-12
申请号：US12218396
申请日：2008-07-15
申请人： Takuya Fujishima , Maarten De Boer , Jordi Bonada , Samuel Roig , Fokke De Jong , Sebastian Streich
发明人： Takuya Fujishima , Maarten De Boer , Jordi Bonada , Samuel Roig , Fokke De Jong , Sebastian Streich
IPC分类号： G10H1/00
CPC分类号： G10H1/0025 , G10H2210/00 , G10H2210/076 , G10H2210/081 , G10H2210/125 , G10H2210/136 , G10H2210/561 , G10H2240/131
摘要： Storage section has stored therein music piece data sets of a plurality of music pieces, each of the music piece data sets including respective tone data of a plurality of fragments of the music piece and respective character values indicative of musical characters of the fragments. Each of the fragments of a selected main music piece is selected as a main fragment, and each one, other than the selected main fragment, of a plurality of fragments of two or more music pieces is selected as a sub fragment. A similarity index value indicative of a degree of similarity between the character value of the main fragment and the character value of the specified sub fragment is calculated. For each of the main fragments, a sub fragment presenting a similarity index value that satisfies a predetermined selection condition is selected for processing the tone data of the main music piece.
摘要翻译： 存储部分存储了多个音乐片段的乐曲数据集，每个乐曲数据集包括音乐片段的多个片段的各个乐曲数据和表示片段的音乐人物的各自的角色值。 选择的主乐曲的每个片段被选择为主片段，并且选择两个或更多个乐曲的多个片段的所选主片段以外的每个片段作为子片段。 计算出表示主要片段的字符值与特定子片段的字符值之间的相似程度的相似度指数值。 对于每个主片段，选择呈现满足预定选择条件的相似度索引值的子片段来处理主乐曲的色调数据。
-
公开(公告)号：US20190236208A1
公开(公告)日：2019-08-01
申请号：US16152435
申请日：2018-10-05
发明人： James Cheng Lee
CPC分类号： G06F16/634 , G06F16/683 , G06F16/951 , G10H1/00 , G10H1/0008 , G10H2210/00 , G10H2240/141 , G10L15/265 , G10L25/51 , H04R1/02 , H04R2420/07
摘要： A smart speaker with music recognition is disclosed, including: a housing, an input device and a control device. The input device receives music information from a music source. The control device includes a processing unit, a storage unit, a communication unit, a voice module and a music recognition module. The storage unit contains a music database. The music recognition module recognizes the feature value of the music information, and uses the feature value to perform melody comparison with the plurality of songs stored in the music database, to search for specific songs and related information in the music database matching the feature value, and upload to the cloud server through the communication unit. After browsing the webpage from the cloud server, the user knows whether a specific song and related information matching the feature value of the music information are stored in the music database.
-
公开(公告)号：US09697812B2
公开(公告)日：2017-07-04
申请号：US14512303
申请日：2014-10-10
申请人： Yamaha Corporation
CPC分类号： G10H1/0008 , G09B15/02 , G10G1/00 , G10G1/02 , G10H1/18 , G10H1/22 , G10H1/38 , G10H2210/00 , G10H2210/571 , G10H2220/005 , G10H2220/015 , G10H2220/036 , G10H2220/041 , G10H2220/091 , G10H2220/241
摘要： When a processor accepts an input of plural notes to be assigned for tone generation, according to a predetermined note determining rule called “assignment type”, the processor selects one or more notes to be sounded in each of plural parts from the accepted notes. The processor controls a display unit to display, for each of the plural parts, the accepted plural notes to be assigned for tone generation. At this time, non-selected one or more notes in respective parts are displayed in one style, and the selected one or more notes in the respective parts are displayed in another style different from the one style. Alternatively, the plural notes to be assigned for tone generation are displayed in one style, and, for each of the plural parts, the selected one or more notes are displayed in another style different from the one style.
-
公开(公告)号：US20130305902A1
公开(公告)日：2013-11-21
申请号：US13982476
申请日：2012-03-12
IPC分类号： G10H1/38
CPC分类号： G10H1/38 , G10H1/00 , G10H1/02 , G10H1/28 , G10H7/02 , G10H2210/00 , G10H2210/576 , G10H2240/145 , G10H2250/541
摘要： An accompaniment data generating apparatus has a storing portion 15 for storing sets of phrase waveform data each related to a chord identified on the basis of a combination of chord type and chord root, and a CPU 9. The CPU 9 carries out a chord information obtaining process for obtaining chord information by which a chord type and a chord root are identified, and a chord note waveform data generating process for generating phrase waveform data indicative of chord notes of the chord root and the chord type identified by the obtained chord information in accordance with the obtained chord information by use of the sets of phrase waveform data stored in the storing portion 15, and outputting the generated data as accompaniment data.
-
公开(公告)号：US20090019996A1
公开(公告)日：2009-01-22
申请号：US12218396
申请日：2008-07-15
申请人： Takuya Fujishima , Maarten De Boer , Jordi Bonada , Samuel Roig , Fokke De Jong , Sebastian Streich
发明人： Takuya Fujishima , Maarten De Boer , Jordi Bonada , Samuel Roig , Fokke De Jong , Sebastian Streich
IPC分类号： G10H1/08
CPC分类号： G10H1/0025 , G10H2210/00 , G10H2210/076 , G10H2210/081 , G10H2210/125 , G10H2210/136 , G10H2210/561 , G10H2240/131
摘要： Storage section has stored therein music piece data sets of a plurality of music pieces, each of the music piece data sets including respective tone data of a plurality of fragments of the music piece and respective character values indicative of musical characters of the fragments. Each of the fragments of a selected main music piece is selected as a main fragment, and each one, other than the selected main fragment, of a plurality of fragments of two or more music pieces is selected as a sub fragment. A similarity index value indicative of a degree of similarity between the character value of the main fragment and the character value of the specified sub fragment is calculated. For each of the main fragments, a sub fragment presenting a similarity index value that satisfies a predetermined selection condition is selected for processing the tone data of the main music piece.
摘要翻译： 存储部分存储了多个音乐片段的乐曲数据集，每个乐曲数据集包括音乐片段的多个片段的各个乐曲数据和表示片段的音乐人物的各自的角色值。 选择的主乐曲的每个片段被选择为主片段，并且选择两个或更多个乐曲的多个片段的所选主片段以外的每个片段作为子片段。 计算出表示主要片段的字符值与特定子片段的字符值之间的相似程度的相似度指数值。 对于每个主片段，选择呈现满足预定选择条件的相似度索引值的子片段来处理主乐曲的色调数据。
-
10.发明授权Voice analysis method and device, voice synthesis method and device, and medium storing voice analysis program 有权语音分析方法和设备，语音合成方法和设备，以及媒体存储语音分析程序公开(公告)号：US09355628B2
公开(公告)日：2016-05-31
申请号：US14455652
申请日：2014-08-08
申请人： Yamaha Corporation
发明人： Makoto Tachibana
CPC分类号： G10H1/361 , G10H7/00 , G10H7/008 , G10H7/02 , G10H2210/00 , G10H2210/051 , G10H2210/066 , G10H2210/091 , G10H2210/095 , G10H2210/325 , G10H2210/331 , G10H2220/155 , G10H2240/121 , G10H2250/455 , G10L13/00 , G10L13/0335 , G10L13/06 , G10L13/10
摘要： A voice analysis method includes a variable extraction step of generating a time series of a relative pitch. The relative pitch is a difference between a pitch generated from music track data, which continuously fluctuates on a time axis, and a pitch of a reference voice. The music track data designate respective notes of a music track in time series. The reference voice is a voice obtained by singing the music track. The pitch of the reference voice is processed by an interpolation processing for a voiceless section from which no pitch is detected. The voice analysis method also includes a characteristics analysis step of generating singing characteristics data that define a model for expressing the time series of the relative pitch generated in the variable extraction step.
摘要翻译： 语音分析方法包括产生相对间距的时间序列的可变提取步骤。 相对间距是由时间轴上连续波动的音轨数据产生的音高与参考声音的音高之间的差。 音乐轨道数据以时间序列指定音乐轨道的各个音符。 参考声音是通过唱歌音乐获得的声音。 参考语音的音调通过对其没有检测到音调的清音部分的内插处理进行处理。 语音分析方法还包括：特征分析步骤，生成规定用于表示在可变提取步骤中生成的相对间距的时间序列的模型的歌唱特征数据。
-
-
-
-
-
-
-
-
-
搜索结果
14 条记录 (耗时 0.014 秒)
