公开(公告)号：US10008193B1

公开(公告)日：2018-06-26

申请号：US15681311

申请日：2017-08-18

Applicant: Mark J. Harvilla

Inventor： Mark J. Harvilla

IPC: G10H1/36

CPC classification number: G10H1/366 ,  G10H1/20 ,  G10H2210/066 ,  G10H2210/081 ,  G10H2210/165 ,  G10H2210/561 ,  G10H2220/011 ,  G10H2250/031 ,  G10H2250/455 ,  G10H2250/481

Abstract: A singing voice conversion system configured to generate a song in the voice of a target singer based on a song in the voice of a source singer is disclosed. The embodiment utilizes two complementary approaches to voice timbre conversion. Both combine the natural prosody of a source singer with the pitch of the target singer—typically the user of the system—to achieve realistic sounding synthetic singing. The system is able to transpose the key of any song to match the automatically determined or desired pitch range of the target singer, thus allowing the system to generalize to any target singer, irrespective of their gender, natural pitch range, and the original pitch range of the song to be sung.

公开(公告)号：US09368093B2

公开(公告)日：2016-06-14

申请号：US14992715

申请日：2016-01-11

Applicant: William R Bachand

Inventor： William R Bachand

IPC: G10G1/04

CPC classification number: G10G1/04 ,  G10G1/00 ,  G10G3/00 ,  G10G3/04 ,  G10H1/0008 ,  G10H1/20 ,  G10H1/383 ,  G10H5/00 ,  G10H7/00 ,  G10H2210/066 ,  G10H2210/081 ,  G10H2210/086 ,  G10H2220/015 ,  G10H2220/121 ,  G10H2220/236 ,  G10H2220/241 ,  G10H2220/451 ,  G10H2250/455 ,  G10H2250/481

Abstract: Recorded media is produced by a method for transcoding music, according to various aspects of the present invention, includes in any practical order: (a) reading indicia of a plurality of notes, each note having pitch and duration; (b) selecting a reference pitch; (c) determining indicia of tone from the reference pitch and the pitch of each note; and (d) outputting for use by an engraving engine, indicia of an apposite staff and indicia of tones and durations corresponding to the plurality of notes.

Abstract translation: 根据本发明的各个方面，通过一种用于对音乐进行代码转换的方法产生记录的媒体，其包括以下任何实际顺序：（a）读取多个音符的标记，每个音符具有间距和持续时间; （b）选择参考音高; （c）从参考音调和每个音符的音调确定音调的标记; 和（d）由雕刻引擎输出，用于指示相应的工作人员的标记和对应于多个音符的音调和持续时间的标记。

公开(公告)号：US08927847B2

公开(公告)日：2015-01-06

申请号：US14301270

申请日：2014-06-10

Applicant: The Board of Trustees of the Leland Stanford Junior University

Inventor： Christopher D. Chafe

IPC: G10H1/04 ,  G10H1/06

CPC classification number: G10H1/08 ,  G10H2250/475 ,  G10H2250/481

Abstract: A time-varying formant is generated at a formant frequency by generating first and second harmonic phase signals having first and second harmonic numbers, respectively, in relation to a modulation frequency. The first and second harmonic phase signals are generated in proportion to a master phase signal, which varies at the modulation frequency, modulo a factor corresponding to their harmonic numbers. First and second sound signals, based on the first and second harmonic phase signals, are frequency modulated to create an arbitrarily rich harmonic spectrum, depending on an FM index. The time-varying formant is generated by generating a time-varying combination of the first and second harmonic sound signals, weighting the first and second harmonic sound signals in accordance with their spectral proximities to the formant frequency. One or more of the harmonic numbers are updated when the time-varying formant frequency passes the frequency of either sound signal.

Abstract translation: 通过分别产生相对于调制频率具有第一和第二谐波数的第一和第二谐波相位信号，以共振峰频率产生时变共振峰。 第一和第二谐波相位信号与主相位信号成比例地生成，该主相位信号以调制频率变化，模数为其谐波数的一个因子。 基于第一和第二谐波相位信号的第一和第二声音信号被频率调制以产生根据FM指数的任意丰富的谐波谱。 时变共振峰通过产生第一和第二谐波声音信号的时变组合，根据它们与共振峰频率的频谱接近度对第一和第二谐波声音信号进行加权来产生。 当时变共振峰频率通过任一声音信号的频率时，更新一个或多个谐波数。

公开(公告)号：US08731695B2

公开(公告)日：2014-05-20

申请号：US13037648

申请日：2011-03-01

Applicant: Markus Sapp

Inventor： Markus Sapp

IPC: G06F17/00 ,  H04H40/54

CPC classification number: G10H7/08 ,  G10H2250/475 ,  G10H2250/481

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for allowing independent control of a formant position and inharmonic content in sound synthesis. In one aspect, this allows continuous shifting of the formant across a spectrum without producing any inharmonic spectral content. In a second aspect, this also makes it possible to generate sound with a defined inharmonic content amount and still move a formant position without changing the inharmonic content amount or to continuously change the amount of inharmonic content without significantly changing the formant position. The disclosed technology uses multiple modulators that are applied to a carrier signal by a weighted sum of their outputs.

Abstract translation: 这里公开的是用于允许在声音合成中独立控制共振峰位置和不协调内容的系统，方法和非暂时的计算机可读存储介质。 在一个方面，这允许共振峰在光谱上连续移动，而不会产生任何不协调的光谱含量。 在第二方面，这也使得可以产生具有定义的非内容含量量的声音，并且仍然移动共振峰位置而不改变不协调内容量，或者在不显着改变共振峰位置的情况下不断地改变不协调内容的量。 所公开的技术使用通过其输出的加权和应用于载波信号的多个调制器。

公开(公告)号：US20120226370A1

公开(公告)日：2012-09-06

申请号：US13037648

申请日：2011-03-01

Applicant: Markus Sapp

Inventor： Markus Sapp

IPC: G06F17/00

CPC classification number: G10H7/08 ,  G10H2250/475 ,  G10H2250/481

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for allowing independent control of a formant position and inharmonic content in sound synthesis. In one aspect, this allows continuous shifting of the formant across a spectrum without producing any inharmonic spectral content. In a second aspect, this also makes it possible to generate sound with a defined inharmonic content amount and still move a formant position without changing the inharmonic content amount or to continuously change the amount of inharmonic content without significantly changing the formant position. The disclosed technology uses multiple modulators that are applied to a carrier signal by a weighted sum of their outputs.

Abstract translation: 这里公开的是用于允许在声音合成中独立控制共振峰位置和不协调内容的系统，方法和非暂时的计算机可读存储介质。 在一个方面，这允许共振峰在光谱上连续移动，而不会产生任何不协调的光谱含量。 在第二方面，这也使得可以产生具有定义的非内容含量量的声音，并且仍然移动共振峰位置而不改变不协调内容量，或者在不显着改变共振峰位置的情况下不断地改变不协调内容的量。 所公开的技术使用通过其输出的加权和应用于载波信号的多个调制器。

公开(公告)号：US20110004476A1

公开(公告)日：2011-01-06

申请号：US12828409

申请日：2010-07-01

Applicant: Keijiro Saino ,  Jordi Bonada

Inventor： Keijiro Saino ,  Jordi Bonada

IPC: G10L13/06

CPC classification number: G10L13/10 ,  G10H1/0008 ,  G10H2210/066 ,  G10H2210/086 ,  G10H2240/155 ,  G10H2250/015 ,  G10H2250/455 ,  G10H2250/481

Abstract: Variation over time in fundamental frequency in singing voices is separated into a melody-dependent component and a phoneme-dependent component, modeled for each of the components and stored into a singing synthesizing database. In execution of singing synthesis, a pitch curve indicative of variation over time in fundamental frequency of the melody is synthesized in accordance with an arrangement of notes represented by a singing synthesizing score and the melody-dependent component, and the pitch curve is corrected, for each of pitch curve sections corresponding to phonemes constituting lyrics, using a phoneme-dependent component model corresponding to the phoneme. Such arrangements can accurately model a singing expression, unique to a singing person and appearing in a melody singing style of the person, while taking into account phoneme-dependent pitch variation, and thereby permits synthesis of singing voices that sound more natural.

Abstract translation: 随着时间的推移，唱歌声音中的基频随时间被分成一个旋律依赖的组件和一个音素依赖组件，为每个组件建模并存储到歌唱综合数据库中。 在执行唱歌合成时，根据由歌唱综合得分和旋律相关分量表示的音符的排列来合成表示旋律基频随时间变化的音调曲线，并且对音调曲线进行校正， 每个音调曲线部分对应于构成歌词的音素，使用与音素对应的音素依赖分量模型。 这样的安排可以准确地模拟唱歌人士独特的歌唱表现，并以人物的旋律歌唱风格出现，同时考虑到音素依赖的音调变化，从而允许合成更自然的歌声。

公开(公告)号：US07523037B2

公开(公告)日：2009-04-21

申请号：US11285601

申请日：2005-11-21

Applicant: Goro Sakata

Inventor： Goro Sakata

IPC: G10L21/00 ,  G10L19/14 ,  G10L13/00 ,  H03G3/00 ,  G10H1/00

CPC classification number: G10L13/033 ,  G10H7/002 ,  G10H2250/285 ,  G10H2250/481 ,  G10L25/90

Abstract: A data synthesis apparatus detects the start of a period of voice waveform data, stores the voice waveform data in a first storage device, starting with its part indicative of the start of the detected period. The apparatus stores in a second storage device musical-sound waveform data including information on pulses having a specified period, and then performs a convolution operation on the voice waveform data stored in the first storage device and the musical-sound waveform data stored in the second storage device, thereby outputting synthesized waveform data synchronized with the specified period of the musical-sound waveform data stored in the second storage device.

Abstract translation: 数据合成装置检测语音波形数据的周期的开始，将语音波形数据存储在第一存储装置中，从表示检测周期的开始的部分开始。 该装置在第二存储装置中存储包括具有指定周期的脉冲的信息的音乐声波形数据，然后对存储在第一存储装置中的声音波形数据和存储在第二存储装置中的音乐声波形数据进行卷积运算 从而输出与存储在第二存储装置中的音乐声波形数据的指定周期同步的合成波形数据。

公开(公告)号：US5665931A

公开(公告)日：1997-09-09

申请号：US312612

申请日：1994-09-27

Applicant: Yutaka Washiyama

Inventor： Yutaka Washiyama

IPC: G10H7/08 ,  G10H1/08 ,  G10H7/10 ,  G10L13/00 ,  G10H7/00 ,  G10H1/06

CPC classification number: G10H7/105 ,  G10H2250/481 ,  G10H2250/491

Abstract: According to the invention, formant waveform signals which are waveforms synthesized from frequency components corresponding to formants of musical tones, are stored and read out or generated. When such formant waveform signal is read out or generated, the density of frequency components of the formant of the formant waveform signal is controlled and also the frequency of a formant center signal which is to be synthesized is a center signal with the formant waveform signal is controlled. In this way, the formant waveform signal is synthesized on the formant center signal. Thus, the density of formant frequency components and the formant center signal frequency can be controlled separately and independently. Further, the kind of formant waveform signal is switched according to musical factors of musical tone. Thus, different kinds of formant waveform signals to be output are switched according to musical factors of musical tones.

Abstract translation: 根据本发明，存储并读出或产生作为对应于音调共振峰的频率分量合成的波形的共振峰波形信号。 当共振峰波形信号被读出或产生时，共振峰波形信号的共振峰的频率分量的密度被控制，并且要合成的共振峰中心信号的频率是共振峰波形信号的中心信号 受控。 以这种方式，共振峰波形信号在共振峰中心信号上合成。 因此，共振峰频率分量和共振峰中心信号频率的密度可以分别独立地控制。 此外，根据乐音的音乐因素来切换共振峰波形信号的种类。 因此，根据音乐音调的因素来切换要输出的不同种类的共振峰波形信号。

公开(公告)号：US4186643A

公开(公告)日：1980-02-05

申请号：US900645

申请日：1978-04-26

Applicant: Kouji Nishibe ,  Nobuaki Kondo

Inventor： Kouji Nishibe ,  Nobuaki Kondo

IPC: G10H1/043 ,  G10H1/053 ,  G10H1/10 ,  G10H1/12 ,  G10H1/14 ,  G10H1/06 ,  G10H5/00

CPC classification number: G10H1/053 ,  G10H1/14 ,  G10H2250/481 ,  Y10S84/04

Abstract: Apparatus for chorus effect in an electronic musical instrument in which a passing circuit for a musical tone signal is obtained from a musical tone signal generator by operation of a key. The passing circuit is connected to a plurality of variable delay circuits which are individually controlled by a plurality of delay control signals generated by a delay control signal generator. The passing circuit for the musical tone signal has a format filter, as well as a keying signal generating circuit. An output terminal of this keying signal generating circuit is connected to a voice production initial stage change control signal generator. The latter control signal generator has an output terminal connected to the musical tone signal generator or the delay control signal generator. The voice production initial stage change control signal generator, furthermore, has a network which generates a control signal which is largely disordered from its steady state and is then damped to restore to the steady state, upon application of a keying signal generated from the keying signal generating circuit. The voice production initial stage change control signal generator, may include a low frequency oscillator for generating a vibrato signal which is disordered by a keying signal generated by the keying signal generating circuit.

Abstract translation: 用于通过键的操作从乐音信号发生器获得乐音信号的通过电路的电子乐器中的合唱效果的装置。 通过电路连接到由延迟控制信号发生器产生的多个延迟控制信号分别控制的多个可变延迟电路。 用于乐音信号的通过电路具有格式滤波器以及键控信号发生电路。 该键控信号发生电路的输出端连接到语音产生初始级变换控制信号发生器。 后一个控制信号发生器具有连接到乐音信号发生器或延迟控制信号发生器的输出端。 此外，语音产生初始级变换控制信号发生器具有产生从其稳定状态很大程度上无序的控制信号的网络，然后在施加从键控信号产生的键控信号时被阻尼以恢复到稳定状态 发电电路。 语音产生初始级变换控制信号发生器可以包括用于产生由键控信号产生电路产生的键控信号无序的颤音信号的低频振荡器。

公开(公告)号：US20060111908A1

公开(公告)日：2006-05-25

申请号：US11285601

申请日：2005-11-21

Applicant: Goro Sakata

Inventor： Goro Sakata

IPC: G10L13/00

CPC classification number: G10L13/033 ,  G10H7/002 ,  G10H2250/285 ,  G10H2250/481 ,  G10L25/90

Abstract: A data synthesis apparatus detects the start of a period of voice waveform data, stores the voice waveform data in a first storage device, starting with its part indicative of the start of the detected period. The apparatus stores in a second storage device musical-sound waveform data including information on pulses having a specified period, and then performs a convolution operation on the voice waveform data stored in the first storage device and the musical-sound waveform data stored in the second storage device, thereby outputting synthesized waveform data synchronized with the specified period of the musical-sound waveform data stored in the second storage device.