知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

30 records (took 0.014 seconds)

    Sound signal processing apparatus, sound signal processing method, and sound signal processing program
    4.
    发明申请
    Sound signal processing apparatus, sound signal processing method, and sound signal processing program 有权
    声音信号处理装置，声音信号处理方法和声音信号处理程序

    公开(公告)号：US20060272488A1

    公开(公告)日：2006-12-07

    申请号：US11439818

    申请日：2006-05-24

    Applicant: Takuya Fujishima ,  Alex Loscos ,  Jordi Bonada ,  Oscar Mayor

    Inventor： Takuya Fujishima ,  Alex Loscos ,  Jordi Bonada ,  Oscar Mayor

    IPC: G10H1/36

    CPC classification number: G10H1/361 ,  G10H2210/061 ,  G10H2210/091 ,  G10H2250/005 ,  G10H2250/015 ,  G10H2250/235 ,  G10L15/142

    Abstract: A sound signal processing apparatus which is capable of correctly detecting expression modes and expression transitions of a song or performance from an input sound signal. A sound signal produced by performance or singing of musical tones is input and divided into frames of predetermined time periods. Characteristic parameters of the input sound signal are detected on a frame-by-frame basis. An expression determining process is carried out in which a plurality of expression modes of a performance or song are modeled as respective states, the probability that a section including a frame or a plurality of continuous frames lies in a specific state is calculated with respect to a predetermined observed section based on the characteristic parameters, and the optimum route of state transition in the predetermined observed section is determined based on the calculated probabilities so as to determine expression modes of the sound signal and lengths thereof.

    Abstract translation: 一种声音信号处理装置，其能够从输入声音信号正确地检测歌曲或演奏的表情模式和表情转换。 通过演奏或唱歌产生的声音信号被输入并分成预定时间段的帧。 在逐帧的基础上检测输入声音信号的特征参数。 执行表达确定处理，其中表演或歌曲的多个表达模式被建模为各自的状态，关于一个或多个关于一个或多个连续帧的部分包括帧或多个连续帧的部分位于特定状态的概率被计算 基于特征参数的预定观测部分，并且基于所计算的概率来确定预定观测部分中的最佳状态转换路线，以便确定声音信号的表达模式及其长度。

    SEAMLESS AUDIO ROLLBACK
    5.
    发明公开
    SEAMLESS AUDIO ROLLBACK 审中-公开

    公开(公告)号：US20240312445A1

    公开(公告)日：2024-09-19

    申请号：US18184525

    申请日：2023-03-15

    Applicant: Roblox Corporation

    Inventor： Frederick William UMMINGER, III

    IPC: G10H7/00 ,  A63F13/54

    CPC classification number: G10H7/008 ,  A63F13/54 ,  A63F2300/6063 ,  G10H2210/026 ,  G10H2210/115 ,  G10H2250/005

    Abstract: A metaverse application performs an audio rollback of a local game state by receiving user input from a user during gameplay of a virtual experience. The metaverse application renders a first game state of gameplay of the virtual experience on the user device based on the user input. The metaverse application receives information about a second game state of gameplay of the virtual experience from a server. The metaverse application determines that there is a discrepancy between the first game state and the second game state. The metaverse application determines an audio gap in the first game state where a modification to game audio is to be inserted. The metaverse application generates replacement audio, wherein a duration of the replacement audio matches a duration of the audio gap. The metaverse application renders a corrected game state on the user device that includes the replacement audio.

    Client-based generation of music playlists from a server-provided subset of music similarity vectors
    7.
    发明授权
    Client-based generation of music playlists from a server-provided subset of music similarity vectors 有权
    来自服务器提供的音乐相似性向量子集的基于客户端的音乐播放列表生成

    公开(公告)号：US07340455B2

    公开(公告)日：2008-03-04

    申请号：US11045930

    申请日：2005-01-27

    Applicant: John Platt ,  Erin Renshaw

    Inventor： John Platt ,  Erin Renshaw

    IPC: G06F17/30

    CPC classification number: G06F17/30758 ,  G06F17/30749 ,  G06F17/30761 ,  G06F17/30772 ,  G06K9/6251 ,  G10H2240/091 ,  G10H2240/135 ,  G10H2240/155 ,  G10H2250/005 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943

    Abstract: A “Music Mapper” automatically constructs a set coordinate vectors for use in inferring similarity between various pieces of music. In particular, given a music similarity graph expressed as links between various artists, albums, songs, etc., the Music Mapper applies a recursive embedding process to embed each of the graphs music entries into a multi-dimensional space. This recursive embedding process also embeds new music items added to the music similarity graph without reembedding existing entries so long a convergent embedding solution is achieved. Given this embedding, coordinate vectors are then computed for each of the embedded musical items. The similarity between any two musical items is then determined as either a function of the distance between the two corresponding vectors. In various embodiments, this similarity is then used in constructing music playlists given one or more random or user selected seed songs or in a statistical music clustering process.

    Abstract translation: “音乐映射器”自动构建用于推断各种音乐之间相似度的集合坐标矢量。 特别地，音乐映射器给出一种表示为各种艺术家，专辑，歌曲等之间的链接的音乐相似图，音乐映射器应用递归嵌入过程将音乐条目中的每一个图形嵌入到多维空间中。 这种递归嵌入过程也将添加到音乐相似图中的新音乐项目嵌入，而不需要重新嵌入现有条目，所以实现了一种融合嵌入解决方案。 给定这个嵌入，然后为每个嵌入的音乐项目计算坐标矢量。 然后将任何两个音乐作品之间的相似度确定为两个对应矢量之间的距离的函数。 在各种实施例中，然后将该相似性用于构造给定一个或多个随机或用户选择的种子歌曲或统计音乐聚类过程中的音乐播放列表。

    Constructing a table of music similarity vectors from a music similarity graph
    8.
    发明申请
    Constructing a table of music similarity vectors from a music similarity graph 有权
    从音乐相似图构建音乐相似性矢量表

    公开(公告)号：US20060107823A1

    公开(公告)日：2006-05-25

    申请号：US10993109

    申请日：2004-11-19

    Applicant: John Platt ,  Erin Renshaw ,  Max Chickering ,  Cormac Herley

    Inventor： John Platt ,  Erin Renshaw ,  Max Chickering ,  Cormac Herley

    IPC: G10H7/00

    CPC classification number: G06F17/30758 ,  G06F17/30749 ,  G06F17/30761 ,  G06F17/30772 ,  G06K9/6251 ,  G10H2240/091 ,  G10H2240/135 ,  G10H2240/155 ,  G10H2250/005 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943

    Abstract: A “Music Mapper” automatically constructs a set coordinate vectors for use in inferring similarity between various pieces of music. In particular, given a music similarity graph expressed as links between various artists, albums, songs, etc., the Music Mapper applies a recursive embedding process to embed each of the graphs music entries into a multi-dimensional space. This recursive embedding process also embeds new music items added to the music similarity graph without reembedding existing entries so long a convergent embedding solution is achieved. Given this embedding, coordinate vectors are then computed for each of the embedded musical items. The similarity between any two musical items is then determined as either a function of the distance between the two corresponding vectors. In various embodiments, this similarity is then used in constructing music playlists given one or more random or user selected seed songs or in a statistical music clustering process.

    Abstract translation: “音乐映射器”自动构建用于推断各种音乐之间相似度的集合坐标矢量。 特别地，音乐映射器给出一种表示为各种艺术家，专辑，歌曲等之间的链接的音乐相似图，音乐映射器应用递归嵌入过程，将每个图形音乐条目嵌入到多维空间中。 这种递归嵌入过程也将添加到音乐相似图中的新音乐项目嵌入，而不需要重新嵌入现有条目，所以实现了一种融合嵌入解决方案。 给定这个嵌入，然后为每个嵌入的音乐项目计算坐标矢量。 然后将任何两个音乐作品之间的相似度确定为两个对应矢量之间的距离的函数。 在各种实施例中，然后将该相似性用于构造给定一个或多个随机或用户选择的种子歌曲或统计音乐聚类过程中的音乐播放列表。

    CONTROLLABLE MUSIC GENERATION
    10.
    发明公开
    CONTROLLABLE MUSIC GENERATION 审中-公开

    公开(公告)号：US20230147185A1

    公开(公告)日：2023-05-11

    申请号：US17521435

    申请日：2021-11-08

    Applicant: LEMON INC.

    Inventor： Zhihao Ouyang ,  Keunwoo Choi

    IPC: G10H1/00 ,  G06N20/00

    CPC classification number: G10H1/0025 ,  G06N20/00 ,  G10H2210/036 ,  G10H2210/115 ,  G10H2210/571 ,  G10H2250/005

    Abstract: The present disclosure describes techniques for controllable music generation. The techniques comprise extracting latent vectors from unlabelled data, the unlabelled data comprising a plurality of music note sequences, the plurality of music note sequences indicating a plurality of pieces of music; clustering the latent vectors into a plurality of classes corresponding to a plurality of music styles; generating a plurality of labelled latent vectors corresponding to the plurality of music styles, each of the plurality labelled latent vectors comprising information indicating features of a corresponding music style; and generating a first music note sequence indicating a first piece of music in a particular music style among the plurality of music styles based at least in part on a particular labelled latent vector among the plurality of labelled latent vectors, the particular labelled latent vector corresponding to the particular music style.

Patent Agency Ranking