Crowd-sourced technique for pitch track generation

    公开(公告)号:US11900904B2

    公开(公告)日:2024-02-13

    申请号:US17651022

    申请日:2022-02-14

    Applicant: SMULE, INC.

    Abstract: Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.

    Method of presenting a piece of music to a user of an electronic device

    公开(公告)号:US09601029B2

    公开(公告)日:2017-03-21

    申请号:US14845519

    申请日:2015-09-04

    Applicant: Simon Gebauer

    Inventor: Simon Gebauer

    Abstract: A method of presenting music to a user of an electronic device comprises the step of providing score data representing the musical score of the piece of music in a graphical representation, audio data representing a recording of the piece of music, and music data representing one or more parts of parts of the piece of music in a digital format such as MIDI or MusicXML. The music data representing a part of the music that has been selected by the user is transformed into part sound signals using a sound generator. The part sound signals and audio sound signals are merged so as to obtain a merged sound signal in which the piece of music as represented by the music data file and by the audio data file are synchronized. Finally, and simultaneously, the sound of the piece of music using the merged sound signal is played audibly, the musical score is displayed on a display, and a sub-portion of the musical score corresponding to a passage of the piece of music which is presently audible is highlighted on the display.

    Automatic tonal analysis of musical scores
    7.
    发明授权
    Automatic tonal analysis of musical scores 有权
    自动色调分析乐谱

    公开(公告)号:US09269339B1

    公开(公告)日:2016-02-23

    申请号:US14728852

    申请日:2015-06-02

    Inventor: Heinrich Taube

    Abstract: Embodiments of the present invention provide a tonal analysis method including the steps of parsing notes of a musical score to generate a time-ordered plurality of sonorities; confirming a plurality of tonal centers each having a tone; accounting a chord of a sonority for a confirmed tonal center to determine whether the chord of the sonority is a functional symbol of the confirmed tonal center; and identifying a tonally stable region of the musical score for a confirmed tonal center, then accounting the chord of each sonority in a tonally stable region as a functional symbol of that tonal center. Embodiments of the present invention provide a non-transitory computer-readable medium which stores the output of the tonal analysis method as sonority data structures associated with theory line entry data structures.

    Abstract translation: 本发明的实施例提供一种音调分析方法,包括分析乐谱的音符以产生时间有序的多个声音的步骤; 确认每个具有音调的多个音调中心; 对于确认的音调中心来说,这是一个声音的和弦,以确定声音的和弦是否是确认的音调中心的功能符号; 并且为确定的音调中心识别音乐稳定区域,然后将音调稳定区域中的每个声音的和弦作为该音调中心的功能符号。 本发明的实施例提供了一种非暂时的计算机可读介质,其将音调分析方法的输出存储为与理论线入口数据结构相关联的声音数据结构。

    MUSICAL PIECE EVALUATION DEVICE, MUSICAL PIECE EVALUATION METHOD, MUSICAL PIECE EVALUATION PROGRAM, AND INFORMATION STORAGE MEDIUM HAVING THE PROGRAM STORED THEREON
    8.
    发明申请
    MUSICAL PIECE EVALUATION DEVICE, MUSICAL PIECE EVALUATION METHOD, MUSICAL PIECE EVALUATION PROGRAM, AND INFORMATION STORAGE MEDIUM HAVING THE PROGRAM STORED THEREON 审中-公开
    音乐评价设备,音乐评价方法,音乐评价评估程序以及存储有程序的信息存储介质

    公开(公告)号:US20150317911A1

    公开(公告)日:2015-11-05

    申请号:US14650080

    申请日:2014-05-19

    Inventor: Taro KAWABATA

    Abstract: A degree of difficulty of a musical piece is comprehensively evaluated also in consideration of a viewpoint of expressions and dynamics of the musical piece. A segment evaluator evaluates a degree of segment difficulty. The degree of segment difficulty indicates the degree of difficulty in performance of a segment (for example, a predetermined number of measures) serving as a part of the musical piece. The segment evaluator divides the musical piece into a plurality of segments, and evaluates the degree of segment difficulty for each of the plurality of segments. The degree of segment difficulty is evaluated in accordance with a predetermined algorithm. A musical piece evaluator evaluates a degree of musical piece difficulty. The degree of musical piece difficulty indicates a degree of difficulty in the performance of the entire musical piece. The musical piece evaluator evaluates the degree of musical piece difficulty of the musical piece based on a change of the degree of segment difficulty within the musical piece.

    Abstract translation: 考虑到乐曲的表现和动态的观点,对乐曲的难度进行综合评价。 段评估者评估段难度。 片段难度表示作为乐曲的一部分的片段(例如,预定数量的拍摄)的演奏难度。 片段评估器将乐曲划分为多个片段,并且评估多个片段中的每一个片段的片段难易度。 根据预定的算法评估段难度。 音乐作品评估者评估音乐作品难度的程度。 音乐作品难度的程度表示整个乐曲的演奏难度。 音乐作品评价者根据音乐作品中的片段难度的变化来评价乐曲的乐曲难度。

    System and method for generating event distribution information
    9.
    发明授权
    System and method for generating event distribution information 有权
    用于生成事件分发信息的系统和方法

    公开(公告)号:US09116605B2

    公开(公告)日:2015-08-25

    申请号:US14083139

    申请日:2013-11-18

    Abstract: A computer system and method for generating event distribution information using an audio file and controlling events corresponding to the user inputs based on the event distribution information. The computer-implemented method includes: extracting a predefined number of event-triggering times from event distribution information, wherein the event distribution information is associated with an audio file currently played on the computer and the event-triggering times are arranged in a sequential order; determining a current play time for the audio file; and controlling event locations corresponding to user inputs on the display of the computer based on a comparison of the current play time and the extracted event-triggering times.

    Abstract translation: 一种用于使用音频文件生成事件分发信息并且基于事件分发信息来控制与用户输入相对应的事件的计算机系统和方法。 计算机实现的方法包括:从事件分发信息提取预定数量的事件触发时间,其中事件分发信息与当前在计算机上播放的音频文件相关联,事件触发时间按顺序排列; 确定音频文件的当前播放时间; 以及基于当前播放时间和提取的事件触发时间的比较来控制与计算机的显示器上的用户输入相对应的事件位置。

Patent Agency Ranking