公开(公告)号：US20150040740A1

公开(公告)日：2015-02-12

申请号：US14450121

申请日：2014-08-01

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Masaru SETOGUCHI

IPC: G10H1/00

CPC classification number: G10H7/02 ,  G10H1/0083 ,  G10H1/18 ,  G10H1/40 ,  G10H2210/076 ,  G10H2210/381 ,  G10H2250/641

Abstract: A sampling device includes: an obtainer that obtains a streaming audio waveform; a detector that detects a tap by a user; a designator that designates a sampling start point on the obtained audio waveform when at least a single tap has been detected by the detector, the designating being performed on the basis of one tap among a plurality of the taps when the plurality of taps are detected; a calculator that calculates a sampling duration on the basis of time intervals between the respective taps when the plurality of taps are detected, the calculating being performed from the sampling start point to a subsequent tap that is performed after the one tap; and a waveform sampler that samples the obtained audio waveform, the sampling starting from the designated sampling start point and ending in accordance with the calculated sampling duration.

Abstract translation: 采样装置包括：获得流音频波形的获取器; 用户检测水龙头的检测器; 当由所述检测器检测到至少一个抽头时，在所获得的音频波形上指定采样开始点的指示符，当检测到所述多个抽头时，基于所述多个抽头中的一个抽头执行所述指定; 计算器，当检测到多个抽头时，基于各个抽头之间的时间间隔计算采样持续时间，该计算从采样开始点执行到在一次抽头之后执行的后续抽头; 以及波形采样器，对所获得的音频波形进行采样，从指定的采样开始点开始采样并根据计算的采样持续时间结束。

公开(公告)号：US20210027753A1

公开(公告)日：2021-01-28

申请号：US17036582

申请日：2020-09-29

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Makoto DANJYO ,  Fumiaki OTA ,  Masaru SETOGUCHI ,  Atsushi NAKAMURA

IPC: G10H1/00 ,  G10H7/00

Abstract: An electronic musical instrument includes at least one processor that, in accordance with a user operation on an operation unit, obtains lyric data and waveform data corresponding to a first tone color; inputs the obtained lyric data to a trained model so as to cause the trained model to output acoustic feature data in response thereto; generates waveform data corresponding to a singing voice of a singer and corresponding to a second tone color that is different from the first tone color, based on the acoustic feature data outputted from the trained model and the obtained waveform data corresponding to the first tone color; and outputs a singing voice based on the generated waveform data corresponding to the second tone color.

公开(公告)号：US20190392798A1

公开(公告)日：2019-12-26

申请号：US16447572

申请日：2019-06-20

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Makoto DANJYO ,  Fumiaki OTA ,  Masaru SETOGUCHI ,  Atsushi NAKAMURA

IPC: G10H1/00 ,  G10H7/00

Abstract: An electronic musical instrument includes: a memory that stores a trained acoustic model obtained by performing machine learning on training musical score data and training singing voice data of a singer; and at least one processor, wherein the at least one processor: in accordance with a user operation on an operation element in a plurality of operation elements, inputs prescribed lyric data and pitch data corresponding to the user operation of the operation element to the trained acoustic model so as to cause the trained acoustic model to output the acoustic feature data in response to the inputted prescribed lyric data and the inputted pitch data, and digitally synthesizes and outputs inferred singing voice data that infers a singing voice of the singer on the basis of the acoustic feature data output by the trained acoustic model.

公开(公告)号：US20190318712A1

公开(公告)日：2019-10-17

申请号：US16384861

申请日：2019-04-15

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Atsushi NAKAMURA ,  Masaru SETOGUCHI ,  Makoto DANJYO ,  Fumiaki OTA

IPC: G10H1/00 ,  G10H1/36 ,  G06N20/00

Abstract: An electronic musical instrument in one aspect of the disclosure includes a keyboard, a processor and a memory that stores musical piece data that includes data of a vocal part, the vocal part including at least first and second notes together with associated first and second lyric parts that are to be successively played at the first and second timings, respectively, wherein if while a digitally synthesized first signing voice corresponding to the first note is being output, a user specifies, via keyboard, a third pitch that is different from the first and second notes prior to the arrival of the second timing, the at least one processor synthesizes a modified first singing voice having the third pitch in accordance with the data of the first lyric part, and causes the digitally synthesized modified first singing voice to be audibly output at the third timing.

公开(公告)号：US20190304327A1

公开(公告)日：2019-10-03

申请号：US16365480

申请日：2019-03-26

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Masaru SETOGUCHI

IPC: G09B15/00 ,  G09B19/00 ,  G10L25/90

Abstract: A singing practice device includes a memory having stored thereon a musical piece data of a musical piece that includes an accompaniment and a vocal part to be sung by a user and at least one processor, wherein when a first segment of the vocal part to be sung by the user during a first time interval arrives while the accompaniment is being played back, the at least one processor determines whether an utterance is input by the user through an audio input device during the first time interval and causes the accompaniment to continue being played back until a point in time immediately before the next time interval only when the utterance was input by the user during the first time interval.

公开(公告)号：US20130182856A1

公开(公告)日：2013-07-18

申请号：US13714962

申请日：2012-12-14

Applicant: Casio Computer Co., Ltd.

Inventor： Masaru SETOGUCHI

IPC: G06F17/00 ,  H04R29/00

CPC classification number: G10H7/00 ,  G06F17/00 ,  G10H1/40 ,  G10H2250/641 ,  H04R3/04 ,  H04R29/00 ,  H04S7/30 ,  H04S2400/15

Abstract: In a recording and playback device of the present invention, when input data exceeding a threshold value is supplied, the CPU records input data for an amount of time corresponding to a single beat in an area specified by syllable number SPLIT in an input buffer IB of the RAM, and after incrementing the syllable number SPLIT, waits until the recorded data becomes silent. The CPU repeats this series of processing until the value of the incremented syllable number SPLIT reaches “4”, and thereby stores input data recorded for an amount of time corresponding to a single beat in each input buffer IB(1) to IB(4) corresponding to syllable numbers SPLIT1 to SPLIT4. Then, the CPU copies the input data to the recording area of the RAM such that these input data are sequentially connected and formed into loop data for an amount of time corresponding to a single bar.

Abstract translation: 在本发明的记录和重放装置中，当提供超过阈值的输入数据时，CPU在与音节编号SPLIT指定的区域中对应于单节拍的时间量的输入数据记录在输入缓冲器IB中 RAM，并且在增加音节数SPLIT之后，等待直到记录的数据变得无声。 CPU重复这一系列处理，直到增量音节数SPLIT的值达到“4”，从而将在每个输入缓冲器IB（1）中对应于单个拍子的时间量记录的输入数据存储到IB（4） 对应于音节号SPLIT1到SPLIT4。 然后，CPU将输入数据复制到RAM的记录区域，使得这些输入数据被顺序地连接并形成为与单个条相对应的时间量的循环数据。