-
公开(公告)号：US09886962B2
公开(公告)日：2018-02-06
申请号：US14635779
申请日：2015-03-02
Applicant: Google Inc.
Inventor： Giovanni Motta , Yang Lu
IPC: G10L19/00 , G10L21/00 , G10L19/018 , H04N21/8358
CPC classification number: G10L19/018 , H04N21/8358
Abstract: A computer-implemented method performed by a data processing apparatus includes receiving an audio signal that includes a frequency-domain representation of an audio file, extracting, from the audio signal, a plurality of frequency-domain data values that correspond to at least a portion of the audio file, compressing the plurality of data values to form a compressed frequency domain value file, and transmitting the compressed frequency domain value file to a server to identify the audio file.
-
公开(公告)号：US09747368B1
公开(公告)日：2017-08-29
申请号：US14097544
申请日：2013-12-05
Applicant: Google Inc.
Inventor： George Alban Heitz, III , Yang Lu
CPC classification number: G06F17/30743 , G06F17/30156
Abstract: A system and method for reducing duplication of music tracks associated with a user account of an online music provider, includes selecting multiple music collections. Selecting at least one of the tracks in the selected music collections, identifying multiple duplicate metadata candidate tracks and multiple duplicate audio candidate tracks. The duplicate metadata candidate tracks are compared to the duplicate audio candidate tracks to identify common duplicate tracks. An audio hash is calculated for each audio file for the common duplicate tracks. An audio hash of one of the common duplicate tracks is selected and compared to the remaining audio hashes of the common duplicate tracks to identify matching tracks. All instances of the matching track in the selected music collections can be replaced with the selected track.
-
公开(公告)号：US20160042761A1
公开(公告)日：2016-02-11
申请号：US14453762
申请日：2014-08-07
Applicant: Google Inc.
Inventor： Giovanni Motta , Yang Lu
CPC classification number: G10L25/51 , G06F17/30026 , G06F17/30743 , G10H1/0033 , G10H2210/031 , G10H2210/091 , G10H2240/141
Abstract: 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.
Abstract translation: 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。
-
Patent Agency Ranking
公开(公告)号：US20170149958A1
公开(公告)日：2017-05-25
申请号：US14949358
申请日：2015-11-23
Applicant: Google Inc.
Inventor： Shijing Xian , Huisheng Wang , Yang Lu
CPC classification number: H04M1/72577 , G06F21/12 , G06F21/31 , G06F21/32 , G06F21/629 , G06F2221/2147 , H04M1/6058 , H04W12/02 , H04W12/06
Abstract: Embodiments help to provide a cross-device security schema for an audio device and a master device to which it is tethered (e.g., a smartphone). An example security scheme provides flexible mechanisms for locking and unlocking the audio device and the device to which it is tethered. For instance, an example security scheme may include: (a) an unlock sync feature that unlocks the audio device and keeps the audio device unlocked whenever the master device is unlocked, (b) a separate audio device unlock process that unlocks the audio device only (without unlocking the master device, and (c) an on-head detection process that, in at least some scenarios, locks the audio device in response to a determination that the audio device is not being worn.
-
公开(公告)号：US09536546B2
公开(公告)日：2017-01-03
申请号：US14453762
申请日：2014-08-07
Applicant: Google Inc.
Inventor： Giovanni Motta , Yang Lu
CPC classification number: G10L25/51 , G06F17/30026 , G06F17/30743 , G10H1/0033 , G10H2210/031 , G10H2210/091 , G10H2240/141
Abstract: 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.
Abstract translation: 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。
-
公开(公告)号：US20160260437A1
公开(公告)日：2016-09-08
申请号：US14635779
申请日：2015-03-02
Applicant: Google Inc.
Inventor： Giovanni Motta , Yang Lu
IPC: G10L19/018
CPC classification number: G10L19/018 , H04N21/8358
Abstract: A computer-implemented method performed by a data processing apparatus includes receiving an audio signal that includes a frequency-domain representation of an audio file, extracting, from the audio signal, a plurality of frequency-domain data values that correspond to at least a portion of the audio file, compressing the plurality of data values to form a compressed frequency domain value file, and transmitting the compressed frequency domain value file to a server to identify the audio file.
Abstract translation: 由数据处理装置执行的由计算机实现的方法包括：接收包括音频文件的频域表示的音频信号，从音频信号中提取对应于至少一部分的多个频域数据值 压缩多个数据值以形成压缩频域值文件，并将压缩的频域值文件发送到服务器以识别该音频文件。
-
公开(公告)号：US20150347388A1
公开(公告)日：2015-12-03
申请号：US14294320
申请日：2014-06-03
Applicant: Google Inc.
Inventor： Yang Lu
CPC classification number: G06F9/454 , G06F16/367 , G06F16/68
Abstract: A digital media store may receive content from a content creator and/or distributor thereof. The distributor may provide the content with a label genre. A first mapping rule may be applied to the label genre to convert it to a canonical genre and the canonical genre may be converted to a regional genre based on the application of a second mapping rule. The regional genre may be presented to a consumer's electronic device along with a translation, if necessary.
Abstract translation: 数字媒体商店可以从内容创作者和/或其分发者接收内容。 经销商可以向内容提供标签类型。 可以将第一映射规则应用于标签类型以将其转换为规范类型，并且可以基于第二映射规则的应用将规范类型转换为区域类型。 如果需要，可以将区域类型与翻译一起提供给消费者的电子设备。
-
公开(公告)号：US09311365B1
公开(公告)日：2016-04-12
申请号：US14019010
申请日：2013-09-05
Applicant: Google Inc.
Inventor： Yang Lu , George Alban Heitz
IPC: G06F17/30
CPC classification number: G06F17/30542 , G06F17/30156 , G06F17/30778
Abstract: A system and method for managing music associated with a user account of an online music provider including receiving a request from a client device to add a song to the user account. A first match search is performed for the corresponding hash pair in a matching pipeline. Each hash pair in the matching pipeline includes a logical link corresponding to a song in a master repository. A second match search is performed when the first match search determines that the song is missing from the master repository. The second match search includes fingerprint matching. The song is associated with the user account when either first or second match search identifies the song to be in the master repository. An upload of the song to the online music provider is requested when the first and second match search determines that the song is missing from the master repository.
Abstract translation: 一种用于管理与在线音乐提供者的用户帐户相关联的音乐的系统和方法，包括接收来自客户端设备的向所述用户帐户添加歌曲的请求。 对匹配管道中的相应散列对执行第一匹配搜索。 匹配流水线中的每个哈希对包括与主存储库中的歌曲相对应的逻辑链路。 当第一匹配搜索确定主存储库中缺少歌曲时，执行第二匹配搜索。 第二匹配搜索包括指纹匹配。 当第一或第二匹配搜索将歌曲标识在主存储库中时，该歌曲与用户帐户相关联。 当第一和第二匹配搜索确定歌曲在主存储库中丢失时，请求将歌曲上传到在线音乐提供商。
-
-
-
-
-
-
-
Search Results
8
records
(took 0.023 seconds)
