公开(公告)号：US20240265902A1

公开(公告)日：2024-08-08

申请号：US18636680

申请日：2024-04-16

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO

IPC: G10H7/00 ,  G10H1/057

CPC classification number: G10H7/002 ,  G10H1/0575 ,  G10H2250/031

Abstract: A sound processing method includes: generating with a trained generative model, for each of a plurality of time points including a first time point, a first acoustic feature amount of a target sound to be generated, by sequentially processing input data including condition data representing conditions of the target sound; generating, for each of the plurality of time points, a time-domain waveform signal representing a waveform of the target sound based on the first acoustic feature amount; and generating, for each of the plurality of time points, a second acoustic feature amount based on the time-domain waveform signal. The input data at the first time point includes the second acoustic feature amount generated before the first time point.

公开(公告)号：US20240129669A1

公开(公告)日：2024-04-18

申请号：US18395901

申请日：2023-12-26

Applicant: YAMAHA CORPORATION

Inventor： Masaru TANAKA ,  Yoshifumi MIZUNO ,  Takashi MORI ,  Akira MAEZAWA ,  Ryunosuke DAIDO ,  Kazunobu KONDO

IPC: H04R3/12 ,  H04R5/04

CPC classification number: H04R3/12 ,  H04R5/04

Abstract: A distribution system includes a device control circuit that receives a first sound signal and a second sound signal that are related to a performance sound to be distributed. The device control circuit also receives meta-data indicating a type of the first sound signal and a type of the second sound signal. The device control circuit also receives sound environment data indicating a sound characteristic of a sound appliance. Based on a combination of the type of the first sound signal and the sound characteristic or a combination of the type of the second sound signal and the sound characteristic, the device control circuit controls the first sound signal or the second sound signal to be output to the sound appliance.

公开(公告)号：US20230386440A1

公开(公告)日：2023-11-30

申请号：US18447051

申请日：2023-08-09

Applicant: Yamaha Corporation

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

IPC: G10H1/12 ,  G10H3/12

CPC classification number: G10H1/12 ,  G10H3/125 ,  G10H2210/031 ,  G10H2250/311 ,  G10H2250/551

Abstract: A sound generation method that is realized by a computer includes receiving a first feature amount sequence in which a musical feature amount changes over time, and using a trained model that has learned an input-output relationship between an input feature amount sequence in which the musical feature amount changes over time at a first fineness and a reference sound data sequence corresponding to an output feature amount sequence in which the musical feature amount changes over time at a second fineness that is higher than the first fineness, to process the first feature amount sequence, thereby generating a sound data sequence corresponding to a second feature amount sequence in which the musical feature amount changes at the second fineness.

公开(公告)号：US20230244646A1

公开(公告)日：2023-08-03

申请号：US18295869

申请日：2023-04-05

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO ,  Keijiro SAINO ,  Masahiro SHIMIZU

IPC: G06F16/21 ,  G06F16/64

CPC classification number: G06F16/219 ,  G06F16/64

Abstract: First time-series data is edited according to a first user instruction, and second time-series data representing a series of features and generated based on the edited first time-series data is edited according to a second user instruction. In response to editing of the first time-series data, the edited first time-series data is saved as a new version in first history data. In response to editing of the second time-series data, the edited second time-series data is saved as a new version in second history data. A first version number and a second version number are designated according to a third user instruction. Third time-series data representing content corresponding to the first time-series data is then generated by using the first version of first time-series data in the first history data, and the second version of second time-series data in the second history data.

公开(公告)号：US20230098145A1

公开(公告)日：2023-03-30

申请号：US18076739

申请日：2022-12-07

Applicant: YAMAHA CORPORATION

Inventor： Keijiro SAINO ,  Ryunosuke DAIDO

IPC: G10H7/00 ,  G10H1/00 ,  G10G1/04

Abstract: An audio processing method, for each time step of a plurality of time steps on a time axis: acquires encoded data that reflects current musical features of a tune for a current time step and musical features of the tune for succeeding time steps succeeding the current time step; acquires control data according to a real-time instruction provided by a user; and generates acoustic feature data representative of acoustic features of a synthesis sound in accordance with first input data including the acquired encoded data and the acquired control data.

公开(公告)号：US20230034572A1

公开(公告)日：2023-02-02

申请号：US17965185

申请日：2022-10-13

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO

IPC: G10L13/033 ,  G06N3/08 ,  G10H1/00 ,  G10L13/06

Abstract: Voice synthesis method and apparatus generate second control data using an intermediate trained model with first input data including first control data designating phonetic identifiers, change the second control data in accordance with a first user instruction provided by a user, generate synthesis data representing frequency characteristics of a voice to be synthesized using a final trained model with final input data including the first control data and the changed second control data, and generate a voice signal based on the generated synthesis data.

公开(公告)号：US20210350783A1

公开(公告)日：2021-11-11

申请号：US17381009

申请日：2021-07-20

Applicant: Yamaha Corporation

Inventor： Ryunosuke DAIDO

IPC: G10L13/00 ,  G10L25/30 ,  G10H7/00

Abstract: A sound signal synthesis method includes inputting control data representing conditions of a sound signal into a neural network, and thereby estimating first data representing a deterministic component of the sound signal and second data representing a stochastic component 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. The neural network has learned a relationship between control data that represents conditions of a sound signal of a reference signal, a deterministic component of the sound signal of the reference signal, and a stochastic component of the sound signal of the reference signal.

公开(公告)号：US20200294484A1

公开(公告)日：2020-09-17

申请号：US16886063

申请日：2020-05-28

Applicant: YAMAHA CORPORATION

Inventor： Ryunosuke DAIDO

IPC: G10L13/033 ,  G10L13/06 ,  G10H1/00 ,  G06N3/08

Abstract: Voice synthesis method and apparatus generate second control data using an intermediate trained model with first input data including first control data designating phonetic identifiers, change the second control data in accordance with a first user instruction provided by a user, generate synthesis data representing frequency characteristics of a voice to be synthesized using a final trained model with final input data including the first control data and the changed second control data, and generate a voice signal based on the generated synthesis data.

公开(公告)号：US20180315444A1

公开(公告)日：2018-11-01

申请号：US16028629

申请日：2018-07-06

Applicant: Yamaha Corporation

Inventor： Ryunosuke DAIDO

IPC: G10L25/90

Abstract: A signal processing device includes a plurality of harmonics attenuation filters configured to have different bandpass characteristics and configured to generate signals to be used for estimation of a fundamental frequency of an input signal by restricting the bandwidth of the input signal. Each of the harmonics attenuation filters comprises a filter that has an accumulator and a comb filter which are connected in cascade. The accumulator is configured to accumulate input signals thereto. The comb filter is configured to output a difference between an input signal to the comb filter and a signal obtained by delaying the input signal to the comb filter.