知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

249 条记录 (耗时 0.032 秒)

    METHOD AND APPARATUS FOR MATCHING MUSIC WITH VIDEO, COMPUTER DEVICE, AND STORAGE MEDIUM
    41.
    发明公开
    METHOD AND APPARATUS FOR MATCHING MUSIC WITH VIDEO, COMPUTER DEVICE, AND STORAGE MEDIUM 审中-公开

    公开(公告)号：US20230290382A1

    公开(公告)日：2023-09-14

    申请号：US18200444

    申请日：2023-05-22

    申请人： Tencent Technology (Shenzhen) Company Limited

    发明人： Xin FENG

    IPC分类号： G11B27/06 ,  G10H1/36

    CPC分类号： G11B27/06 ,  G10H1/368 ,  G10H2240/141

    摘要： This application relates to a method for matching music with a video performed by a computer device, and a storage medium. The method includes: determining a cut speed of a video; determining a long-time audio speed corresponding to each of a plurality of pieces of candidate music according to a high-scale point and a music duration of the candidate music; selecting matched music from the pieces of candidate music according to the cut speed and the corresponding long-time audio speeds; determining, according to a video duration of the video and a high-scale point corresponding to the matched music, a short-time audio speed corresponding to each music clip in the matched music; and determining a target music clip in the matched music according to the cut speed of the video and the corresponding short-time audio speed, and synthesizing the target music clip and the video to obtain a target video.

    SYSTEMS AND METHODS FOR ANALYZING COMPONENTS OF AUDIO TRACKS
    44.
    发明申请
    SYSTEMS AND METHODS FOR ANALYZING COMPONENTS OF AUDIO TRACKS 审中-公开

    公开(公告)号：US20170236504A1

    公开(公告)日：2017-08-17

    申请号：US15435664

    申请日：2017-02-17

    申请人： RMXHTZ, Inc.

    发明人： Sam Brooker ,  Eugene Melnichenko ,  Matt Wilder ,  Seth Johnson

    IPC分类号： G10H1/00 ,  G06Q50/18

    CPC分类号： G10H1/0008 ,  G06Q50/184 ,  G10H2210/125 ,  G10H2240/041 ,  G10H2240/141 ,  G10H2240/181 ,  G10H2250/235 ,  G10H2250/285 ,  G10H2250/305

    摘要： A method is described comprising receiving a stem signal and an audio mix signal, wherein the audio mix signal comprises information of the stem signal. The method includes applying a first transform to the stem signal to provide a first stem spectrum, applying a second transform to the stem signal to provide a second stem spectrum, generating a plurality of mix signals using the audio mix signal, applying a first transform to each mix signal of the plurality of mix signals to provide a corresponding first mix signal spectrum, applying a second transform to each mix signal of the plurality of mix signals to provide a corresponding second mix signal spectrum, and using information of the first stem spectrum, the second stem spectrum, a first mix signal spectrum, or a second mix signal spectrum to detect the information of the stem signal in the audio mix signal.

    Finding differences in nearly-identical audio recordings
    45.
    发明授权
    Finding differences in nearly-identical audio recordings 有权
    发现差不多相同的录音

    公开(公告)号：US09536546B2

    公开(公告)日：2017-01-03

    申请号：US14453762

    申请日：2014-08-07

    申请人： Google Inc.

    发明人： Giovanni Motta ,  Yang Lu

    IPC分类号： G06F17/00 ,  G10L25/51 ,  G06F17/30

    CPC分类号： G10L25/51 ,  G06F17/30026 ,  G06F17/30743 ,  G10H1/0033 ,  G10H2210/031 ,  G10H2210/091 ,  G10H2240/141

    摘要： Systems and techniques are provided for finding differences in nearly-identical audio recordings. A first version of an audio recording may be received. A second version of the audio recording may be received. A difference between the first version of the audio recording and the second version of the audio recording may be determined using time domain analysis and frequency domain analysis. The difference may be stored in a difference set. The difference set may allow the first version of the audio recording to be distinguished from the second version of the audio recording. The audio recording may be a music track. The first version of the audio recording may be an explicit version of the music track. The second version of the audio recording may be an edited version of the music track.

    摘要翻译： 提供了系统和技术，用于发现几乎完全相同的音频记录的差异。 可以接收第一版本的音频记录。 可以接收第二版本的音频记录。 可以使用时域分析和频域分析来确定音频记录的第一版本和音频记录的第二版本之间的区别。 差值可以存储在差值集中。 差异集可以允许音频记录的第一版本与音频记录的第二版本区分开。 音频记录可以是音乐轨道。 音频记录的第一版本可以是音乐轨道的显式版本。 音频录制的第二版本可以是音乐曲目的编辑版本。

    Musically contextual audio advertisements
    46.
    发明授权
    Musically contextual audio advertisements 有权
    音乐上下文音频广告

    公开(公告)号：US09459828B2

    公开(公告)日：2016-10-04

    申请号：US15053656

    申请日：2016-02-25

    申请人： Brian K. Ales

    发明人： Brian K. Ales

    IPC分类号： G06F17/00 ,  G06F3/16 ,  G10H1/00

    CPC分类号： G06F3/165 ,  G06K9/0053 ,  G06K9/6215 ,  G06Q30/0241 ,  G10H1/0025 ,  G10H1/40 ,  G10H2210/076 ,  G10H2210/081 ,  G10H2210/125 ,  G10H2210/335 ,  G10H2210/561 ,  G10H2240/075 ,  G10H2240/141 ,  G11B20/10527 ,  G11B27/007 ,  G11B27/10 ,  G11B27/105 ,  G11B27/28 ,  G11B2020/10555

    摘要： Audio advertisements for music services can be created and played to minimize any perceived discontinuity by a listener from a preceding song. Specifically, a voice-over content item (e.g., a spoken advertisement produced without music) may combined with a non-song musical content item (e.g., backing music specifically produced for advertisements) to create an audio advertisement to be played after a song on a streaming music service. The non-song musical content item may be selected based on its similarity to the preceding song (e.g., genre, tempo, or harmony) and/or a musical preference of a user (e.g., a preferred genre obtained through a user's music service account and/or selected by the user). The genre of both the preceding song and a musical preference of a user may be used to select a non-song musical content item genre by a weighting that determines the probability of the genre used for an advertisement.

    摘要翻译： 可以创建和播放用于音乐服务的音频广告，以最小化来自前一首歌曲的收听者的任何感知到的不连续性。 具体来说，语音内容项目（例如，没有音乐产生的口语广告）可以与非歌曲音乐内容项目（例如，为广告专门制作的支持音乐）相结合，以创建要在歌曲开始之后播放的音频广告 流媒体音乐服务。 非歌曲音乐内容项目可以基于其与前一首歌曲（例如，类型，速度或和声）的相似性和/或用户的音乐偏好（例如，通过用户的音乐服务帐户获得的优选类型）来选择 和/或由用户选择）。 上述歌曲的类型和用户的音乐偏好可以用于通过确定用于广告的类型的概率的加权来选择非歌曲音乐内容项目类型。

    Performance data search using a query indicative of a tone generation pattern
    47.
    发明授权
    Performance data search using a query indicative of a tone generation pattern 有权
    使用表示音色生成模式的查询的演奏数据搜索

    公开(公告)号：US09449083B2

    公开(公告)日：2016-09-20

    申请号：US13451336

    申请日：2012-04-19

    申请人： Daichi Watanabe ,  Takuya Fujishima

    发明人： Daichi Watanabe ,  Takuya Fujishima

    IPC分类号： G06F17/30 ,  G06Q30/02 ,  G10H1/00 ,  G10H1/38

    CPC分类号： G06F17/30758 ,  G06F17/30533 ,  G06F17/30743 ,  G06F17/30864 ,  G06Q30/02 ,  G10H1/0008 ,  G10H1/383 ,  G10H1/386 ,  G10H2210/361 ,  G10H2240/141

    摘要： A user inputs, as a query pattern, a desired search-object rhythm pattern using a control, corresponding to a desired one of a plurality of performance parts constituting a performance data set (automatic accompaniment data set), in a rhythm input device. An input rhythm pattern storage section stores the input rhythm pattern (query pattern) into a RAM on the basis of a clock signal output from a bar line clock output section and input trigger data. A part identification section identifies a search-object performance part corresponding to the user-operated control. For the identified performance part, a rhythm pattern search section searches an automatic accompaniment database for an automatic accompaniment data set including a rhythm pattern that matches, i.e. has the highest similarity to, the input rhythm pattern (query pattern).

    摘要翻译： 在节奏输入装置中，用户使用与构成演奏数据组（自动伴奏数据组）的多个演奏部分中期望的一个对应的控制来输入期望的搜索对象节奏模式作为查询模式，作为查询模式。 输入节奏模式存储部分基于从条形线时钟输出部分输出的时钟信号和输入触发数据将输入节奏模式（查询模式）存储到RAM中。 部件识别部件识别与用户操作的控制对应的搜索对象性能部件。 对于所识别的演奏部分，节奏模式搜索部分在自动伴奏数据库中搜索包括与输入节奏模式（查询模式）具有最高相似性的节奏模式的自动伴奏数据集。

    Derivation of probabilistic score for audio sequence alignment
    48.
    发明授权
    Derivation of probabilistic score for audio sequence alignment 有权
    推导音频序列比对的概率分数

    公开(公告)号：US09384758B2

    公开(公告)日：2016-07-05

    申请号：US14754539

    申请日：2015-06-29

    申请人： Google Inc.

    发明人： Pedro Gonnet Anders

    IPC分类号： G10L19/12 ,  G10L25/51

    CPC分类号： G10L25/51 ,  G06F17/30743 ,  G10H2210/066 ,  G10H2240/141

    摘要： A match score provides a semantically-meaningful quantification of the aural similarity of two chromae from two corresponding audio sequences. The match score can be applied to the chroma pairs of two corresponding audio sequences, and is independent of the lengths of the sequences, thereby permitting comparisons of matches across subsequences of different length. Accordingly, a single cutoff match score to identify “good” audio subsequence matches can be determined and has both good precision and good recall metrics. A function for determining the match score is determined by establishing a function PM indicating probabilities that chroma correspondence scores indicate semantic correspondences, and a function PR indicating probabilities that chroma correspondence scores indicate random correspondences, repeatedly updating PM and the match function based on existing values of PM and the match function as applied to audio subsequences with known semantic correspondences.

    摘要翻译： 匹配分数从两个对应的音频序列提供了两个色度的听觉相似性的语义上有意义的量化。 匹配分数可以应用于两个对应的音频序列的色度对，并且与序列的长度无关，从而允许比较不同长度的子序列的匹配。 因此，可以确定用于识别“良好”音频子序列匹配的单个截止匹配分数，并且具有良好的精度和良好的回忆度量。 通过建立指示色度对应分数表示语义对应关系的概率的函数PM和表示色度对应分数表示随机对应关系的概率的功能PR，基于现有的值的重新更新PM和匹配函数来确定匹配分数的功能 PM和匹配功能应用于具有已知语义对应关系的音频子序列。

    ACOUSTIC MUSIC SIMILARITY DETERMINER
    49.
    发明申请
    ACOUSTIC MUSIC SIMILARITY DETERMINER 有权
    声乐音乐相似性测定器

    公开(公告)号：US20160125859A1

    公开(公告)日：2016-05-05

    申请号：US14899004

    申请日：2014-06-09

    申请人： Nokia Technologies Oy

    发明人： Antti Eronen ,  Jussi Leppanen

    IPC分类号： G10H1/00

    CPC分类号： G10H1/0008 ,  G06F17/30743 ,  G10H2210/041 ,  G10H2210/091 ,  G10H2240/141 ,  G10L25/51

    摘要： It is inter alia disclosed a method comprising: determining a divergence measure between a statistical distribution of audio features of a first audio track and a statistical distribution of audio features of at least one further audio track; determining a divergence measure threshold value from at least the divergence measure between the statistical distribution of audio features of a first audio track and the statistical distribution of audio features of the at least one further audio track; and comparing the divergence measure with the divergence measure threshold value.

    摘要翻译： 特别地，公开了一种方法，包括：确定第一音频轨道的音频特征的统计分布和至少一个另外的音频轨道的音频特征的统计分布之间的发散度量; 从至少第一音频轨道的音频特征的统计分布与所述至少一个另外的音频轨道的音频特征的统计分布之间的至少所述发散度量度确定发散测量阈值; 并将发散度与发散度阈值进行比较。

    GENERATION OF A SIGNATURE OF A MUSICAL AUDIO SIGNAL
    50.
    发明申请
    GENERATION OF A SIGNATURE OF A MUSICAL AUDIO SIGNAL 审中-公开
    音乐音频信号的签名生成

    公开(公告)号：US20160005412A1

    公开(公告)日：2016-01-07

    申请号：US14769998

    申请日：2014-02-25

    申请人： INSTITUT MINES TELECOM

    发明人： Sebastien FENET ,  Yves GRENIER ,  Richard Gael

    IPC分类号： G10L19/018 ,  G06F17/30 ,  G10L25/54

    CPC分类号： G10L19/018 ,  G06F17/30743 ,  G10H1/0008 ,  G10H2210/051 ,  G10H2210/081 ,  G10H2220/005 ,  G10H2240/141 ,  G10H2250/031 ,  G10L25/54 ,  H04H60/37 ,  H04H60/58

    摘要： The invention concerns a method for generating a signature of a musical audio signal of a given duration, the method comprising the following steps: —modelling (104) the musical audio signal to obtain, for each frequency band of a set of n frequency bands, a diagram representing the energy of the audio signal for the frequency band, on the basis of the time during said given duration; —determining (103) musical transition times tk of the audio signal during the given duration; —associating (105) each musical transition time tk with an item of local information comprising a vector of n values representative, respectively, of the energy of the audio signal in each of the n diagrams obtained between musical transition time tk and a subsequent musical transition time tk+1 and/or a vector of n values representative, respectively, of the energy of the audio signal in each of the n diagrams obtained between musical transition time tk and a preceding musical transition time tk−1; —determining (106), on the basis of the local information associated with each musical transition time tk, a key associated with the musical transition time, the determined keys forming a first set of keys of the audio signal; —generating (107) a signature of the musical audio signal comprising pairs of keys from the first set of keys and associated musical transition times tk.

    摘要翻译： 本发明涉及一种用于产生给定持续时间的音乐音频信号的签名的方法，该方法包括以下步骤： - 为了获得（104）音乐音频信号以获得对于一组n个频带的每个频带， 基于所述给定持续时间内的时间，表示频带的音频信号的能量的图; 在给定持续时间内确定（103）音频信号的音乐转换时间tk; （105）每个音乐过渡时间tk与本地信息项分别包括分别代表在音乐转换时间tk和随后的音乐转换之间获得的每个n图中的音频信号的能量的n个值的矢量 时间tk + 1和/或n个值的矢量分别代表在音乐转换时间tk和先前的音乐转换时间tk-1之间获得的每个n个图形中的音频信号的能量; - 基于与每个音乐过渡时间tk相关联的本地信息确定（106）与音乐转换时间相关联的键，所确定的键形成音频信号的第一组键; 产生（107）音乐音频信号的签名，该签名包括来自第一组密钥和相关联的音乐过渡时间t k的键对。