公开(公告)号：US20220084492A1

公开(公告)日：2022-03-17

申请号：US17534664

申请日：2021-11-24

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO

IPC: G10H7/08 ,  G10L25/30

Abstract: A method analyzes a reference signal representing a sound in each of analysis periods to obtain a series of phase spectra and a series of amplitude spectra over the analysis periods; adjusts, for each respective analysis period, phases of each harmonic component in a respective phase spectrum to be a target value at a pitch mark corresponding to the respective analysis period; synthesizes a first sound signal over the analysis periods based on the adjusted series of phase spectra of the reference signal and the obtained series of amplitude spectra of the reference signal; prepares training data including first control data representing of generative conditions of the reference signal and the first sound signal synthesized from the reference signal; and establishes, through machine learning using the training data, the generative model that generates a second sound signal based on second control data representing generative conditions of the second sound signal.

公开(公告)号：US20210256960A1

公开(公告)日：2021-08-19

申请号：US17307322

申请日：2021-05-04

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Merlijn BLAAUW ,  Jordi BONADA

IPC: G10L13/047 ,  G10L13/033 ,  G10L13/06

Abstract: An information processing system includes at least one memory storing a program and at least one processor. The at least one processor implements the program to input a piece of sound source data representative of a sound source, a piece of style data representative of a performance style, and synthesis data representative of sounding conditions into a synthesis model generated by machine learning, and to generate, using the synthesis model, feature data representative of acoustic features of a target sound of the sound source to be generated in the performance style and according to the sounding conditions, and to generate an audio signal corresponding to the target sound using the generated feature data.

公开(公告)号：US20180211644A1

公开(公告)日：2018-07-26

申请号：US15928558

申请日：2018-03-22

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Hiraku KAYAMA ,  Jyunya ISHIKAWA

IPC: G10H1/36 ,  G10H1/00 ,  G10L21/007

CPC classification number: G10H1/366 ,  G10H1/0008 ,  G10H1/125 ,  G10H2210/005 ,  G10H2210/036 ,  G10H2210/066 ,  G10H2240/081 ,  G10L21/003 ,  G10L21/007 ,  H03G9/00 ,  H03G9/025 ,  H04R3/00 ,  H04R2410/00

Abstract: A method for processing an input sound signal of singing voice, to obtain a sound signal with an impression different from the input sound signal, includes: selecting a genre from among a plurality of tune genres in accordance with a selection operation by a user, setting, to a first unit, a set of first parameters corresponding to the selected genre, displaying a first impression identifier corresponding to the selected genre for a first control of a first user parameter in the set of first parameters, changing the first user parameter in accordance with a change operation on the first control by the user, and strengthening, by the first unit, signal components within a particular frequency band of the sound signal, in accordance with the set of first parameters including the first user parameters.

公开(公告)号：US20240015368A1

公开(公告)日：2024-01-11

申请号：US18474371

申请日：2023-09-26

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Takashi MORI

IPC: H04N21/81 ,  H04N21/442

CPC classification number: H04N21/8106 ,  H04N21/44213

Abstract: A distribution system includes an obtaining circuit, a determination circuit, a generation circuit, and a distribution circuit. The obtaining circuit obtains reaction information from a terminal device of a viewer of the content. The reaction information indicates a reaction of the viewer to the content. The determination circuit determines whether the reaction information is first reaction information or second reaction information. The first reaction information indicates a first reaction made by equal to or more than a predetermined number of viewers. The second reaction information is different from the first reaction information and indicates a second reaction made by less than the predetermined number of viewers. The generation circuit generates an audience sound in a case of the first reaction information. The distribution circuit transmits the audience sound to the plurality of terminal devices.

公开(公告)号：US20230395046A1

公开(公告)日：2023-12-07

申请号：US18447071

申请日：2023-08-09

Applicant: Yamaha Corporation

Inventor： Keijiro SAINO ,  Ryunosuke DAIDO ,  Bonada JORDI ,  Blaauw MERLIJN

IPC: G10H1/00

CPC classification number: G10H1/0008 ,  G10H2250/005 ,  G10H2220/091

Abstract: A sound generation method that is realized by a computer includes receiving a representative value of a musical feature amount for each of a plurality of sections of a musical note, and using a trained model to process a first feature amount sequence in accordance with the representative value for each section, thereby generating a sound data sequence corresponding to a second feature amount sequence in which the musical feature amount changes continuously.

公开(公告)号：US20210366454A1

公开(公告)日：2021-11-25

申请号：US17392579

申请日：2021-08-03

Applicant: Yamaha Corporation

Inventor： Ryunosuke DAIDO

IPC: G10H7/02 ,  G10H1/08

Abstract: A sound signal synthesis method includes generating first data representing a deterministic component of a sound signal based on second control data representing conditions of the sound signal, generating, using a first generation model, second data representing a stochastic component of the sound signal based on the first data and first control data representing conditions of the sound signal, and combining the deterministic component represented by the first data and the stochastic component represented by the second data and thereby generating the sound signal.

公开(公告)号：US20200342848A1

公开(公告)日：2020-10-29

申请号：US16924463

申请日：2020-07-09

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO

IPC: G10L13/047

Abstract: A voice synthesis method designates a target feature of a voice to be synthesized; specifies harmonic frequencies for a plurality of respective harmonic components of the voice and an amplitude spectrum envelope of the voice; specifies a harmonic amplitude distribution of each of the plurality of respective harmonic components based on (i) the target feature, (ii) the amplitude spectrum envelope, and (iii) the harmonic frequency specified for the respective harmonic component, the harmonic amplitude distribution representing a distribution of amplitudes in a unit band with a peak amplitude corresponding to the respective harmonic component; and generates a frequency spectrum of the voice with the target feature based on harmonic amplitude distributions specified for each of the plurality of respective harmonic components and the amplitude spectrum envelope.

公开(公告)号：US20200294486A1

公开(公告)日：2020-09-17

申请号：US16885827

申请日：2020-05-28

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Masahiro SHIMIZU

IPC: G10L13/04 ,  G10L25/30 ,  G10L25/93

Abstract: A voice synthesis method includes: supplying a first trained model with control data including phonetic identifier data to generate a series of frequency spectra of harmonic components; supplying a second trained model with the control data to generate a waveform signal representative of non-harmonic components; and generating a voice signal including the harmonic components and the non-harmonic components based on the series of frequency spectra of the harmonic components generated by the first trained model and the waveform signal representative of the non-harmonic components generated by the second trained model.

公开(公告)号：US20190130893A1

公开(公告)日：2019-05-02

申请号：US16233421

申请日：2018-12-27

Applicant: YAMAHA CORPORATION

Inventor： Yuji HISAMINATO ,  Ryunosuke DAIDO ,  Keijiro SAINO ,  Jordi BONADA ,  Merlijn BLAAUW

IPC: G10L13/033 ,  G10L13/07 ,  G10L25/18

Abstract: A voice synthesis method includes: sequentially acquiring voice units in accordance with synthesis information for synthesizing voices; generating statistical spectral envelopes using a statistical model in accordance with the synthesis information for synthesizing the voices; and concatenating the sequentially acquired voice units and modifying a frequency spectral envelope of each voice unit in accordance with the generated statistical spectral envelope, thereby synthesizing a voice signal based on the concatenated voice units having the modified frequency spectra.

公开(公告)号：US20180122397A1

公开(公告)日：2018-05-03

申请号：US15800488

申请日：2017-11-01

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Hiraku KAYAMA

IPC: G10L21/02

CPC classification number: G10L21/0205 ,  G10L21/007

Abstract: A sound processing method includes a step of applying a nonlinear filter to a temporal sequence of spectral envelope of an acoustic signal, wherein the nonlinear filter smooths a fine temporal perturbation of the spectral envelope without smoothing out a large temporal change. A sound processing apparatus includes a smoothing processor configured to apply a nonlinear filter to a temporal sequence of spectral envelope of an acoustic signal, wherein the nonlinear filter smooths a fine temporal perturbation of the spectral envelope without smoothing out a large temporal change.