公开(公告)号：US20230421865A1

公开(公告)日：2023-12-28

申请号：US18463427

申请日：2023-09-08

Applicant: YAMAHA CORPORATION

Inventor： Kentaro NOTO ,  Katsumi ISHIKAWA ,  Futoshi SHIRAKIHARA

IPC: H04N21/845 ,  H04N21/2187

CPC classification number: H04N21/8456 ,  H04N21/2187

Abstract: A content data processing method generates a first-time code indicating an elapsed time from a start of the live event, generates first content data from first data, which includes the one of the audio or video data, received from the live event by adding, to the first data, the first-time code with a first start time and a first end time associated with the first data, and generates a second-time code indicating a duration associated with the first data reflecting the first start time and the first end time.

公开(公告)号：US20250133361A1

公开(公告)日：2025-04-24

申请号：US19000930

申请日：2024-12-24

Applicant: YAMAHA CORPORATION

Inventor： Futoshi SHIRAKIHARA ,  Ryo MATSUDA ,  Yoshinari NAKAMURA ,  Yuya TAKENAKA ,  Katsumi ISHIKAWA ,  Akio OHTANI ,  Kazuhiko YAMAMOTO ,  Takuya FUJISHIMA

IPC: H04S7/00 ,  G06Q30/04

Abstract: A method of processing sound includes arranging objects of a plurality of performers in a virtual space. The method also includes receiving a plurality of sound signals respectively corresponding to the plurality of performers. The method also includes obtaining, using a trained model, sound volume adjustment parameters respectively for the plurality of performers. The trained model is trained to learn a relationship between each sound signal, among the plurality of sound signals, that corresponds to each performer of the plurality of performers and each sound volume adjustment parameter, among the sound volume adjustment parameters, that corresponds to the each sound signal. The method also includes adjusting and mixing sound volumes respectively of the plurality of sound signals based on the sound volume adjustment parameters obtained using the trained model.

公开(公告)号：US20230014315A1

公开(公告)日：2023-01-19

申请号：US17952077

申请日：2022-09-23

Applicant: Yamaha Corporation

Inventor： Akira MAEZAWA ,  Katsumi ISHIKAWA

IPC: G10H1/00 ,  G06N20/00

Abstract: A trained model establishment method realized by a computer includes acquiring a plurality of datasets each of which is formed by a combination of first performance data of a first performance by a performer, second performance data of a second performance performed together with the first performance, and a satisfaction label indicating a degree of satisfaction of the performer, and executing machine learning of a satisfaction estimation model by using the plurality of datasets. In the machine learning, the satisfaction estimation model is trained such that, for each of the datasets, a result of estimating a degree of satisfaction the performer from the first performance data and the second performance data matches the degree of the satisfaction indicated by the satisfaction label.

公开(公告)号：US20250014554A1

公开(公告)日：2025-01-09

申请号：US18887154

申请日：2024-09-17

Applicant: YAMAHA CORPORATION

Inventor： Katsumi ISHIKAWA ,  Takuya FUJISHIMA ,  Takuma TAKEMOTO ,  Yoshinari NAKAMURA ,  Rei NISHIYAMA ,  Yoshikazu NOFUJI

IPC: G10H1/36 ,  G10H1/00

Abstract: A method for outputting data according to an embodiment includes acquiring performance data generated by a performance operation, specifying a musical score performance position in a predetermined musical score based on the performance data, reproducing first data based on the musical score performance position, assigning first position information, corresponding to a first virtual position set corresponding to the first data, to the first data, and outputting playback data including the first data to which the first position information is assigned.

公开(公告)号：US20170178622A1

公开(公告)日：2017-06-22

申请号：US15381201

申请日：2016-12-16

Applicant: Yamaha Corporation

Inventor： Katsumi ISHIKAWA ,  Osamu OHSHIMA ,  Eiji AKAZAWA ,  Naoki YAMAMOTO ,  Yuki MURAKAMI

IPC: G10L13/10 ,  G10L13/04 ,  A63F13/54 ,  G10L13/033

CPC classification number: G10L13/10 ,  A63F13/54 ,  A63F13/814 ,  G10H1/361 ,  G10H2250/455 ,  G10L13/033 ,  G10L13/04

Abstract: An information processing device determines whether a predetermined condition with regard to information processing has been met, changes a character for vocalization when the predetermined condition has been met, and generates a sound signal of a synthesized voice obtained by vocalizing the character for vocalization that has been changed.

公开(公告)号：US20230007421A1

公开(公告)日：2023-01-05

申请号：US17942732

申请日：2022-09-12

Applicant: YAMAHA CORPORATION

Inventor： Futoshi SHIRAKIHARA ,  Tadashi MORIKAWA ,  Kentaro NOTO ,  Katsumi ISHIKAWA ,  Hiraku OKUMURA

IPC: H04S7/00 ,  H04R3/12 ,  H04S3/00

Abstract: A live data distribution method obtains first sound source information according to sound of a first sound source generated at a first location of the first venue and position information of the first sound source, and second sound source information according to a second sound source including an ambient sound generated at a second location of the first venue, as distribution data, distributes the distributed data to the second venue, and renders the distribution data and providing first sound of the first sound source having been performed with localization processing based on the position information of the first sound source, and second sound of the second sound source, at the second venue.

公开(公告)号：US20250014266A1

公开(公告)日：2025-01-09

申请号：US18893334

申请日：2024-09-23

Applicant: Yamaha Corporation

Inventor： Katsumi ISHIKAWA ,  Kentaro NOTO ,  Akio OHTANI

IPC: G06T15/20 ,  H04S7/00

Abstract: A video processing method places an object in a three-dimensional space and outputs a video of a live event as viewed from a viewpoint position set in the three-dimensional space. The video processing method sets a first viewpoint position based on a first factor being a factor related to the object. The video processing method also outputs the video of the live event as viewed from the first viewpoint position, receives a second factor being a factor related to a sound of the live event, and calculates a relative position to the object according to the second factor. The video processing method also changes the first viewpoint position to a second viewpoint position based on the calculated relative position, and outputs the video of the live event as viewed from the second viewpoint position.

公开(公告)号：US20230386495A1

公开(公告)日：2023-11-30

申请号：US18366865

申请日：2023-08-08

Applicant: YAMAHA CORPORATION

Inventor： Takuma TAKEMOTO ,  Katsumi ISHIKAWA ,  Akio OHTANI

IPC: G10L21/028 ,  G10L25/51 ,  H04R5/033

CPC classification number: G10L21/028 ,  H04R5/033 ,  G10L25/51

Abstract: A sound processing method obtains first audio data representing first sound, obtains second audio data representing second sound created in advance, analyzes the first audio data, compares the second audio data with an analysis result of the analyzing, reproduces third audio data from the second audio data by omitting a type of sound from the second sound that matches a type of sound in the first sound, based on a comparison result of the comparing, and outputs an audio signal representing the reproduced third audio data.

公开(公告)号：US20230005464A1

公开(公告)日：2023-01-05

申请号：US17942644

申请日：2022-09-12

Applicant: YAMAHA CORPORATION

Inventor： Futoshi SHIRAKIHARA ,  Tadashi MORIKAWA ,  Kentaro NOTO ,  Katsumi ISHIKAWA ,  Hiraku OKUMURA

IPC: G10K15/08 ,  H04S7/00

Abstract: A live data distribution method obtains information on a sound source according to sound generated at the first venue, and information on space reverberation, as distribution data, distributes the distribution data to the second venue, and renders the distribution data and providing sound according to the distribution data at the second venue.

公开(公告)号：US20190333406A1

公开(公告)日：2019-10-31

申请号：US16460377

申请日：2019-07-02

Applicant: Yamaha Corporation

Inventor： Takuya FUJISHIMA ,  Katsumi ISHIKAWA ,  Shinya SAKURADA ,  Toshiyuki HATA ,  Norihiro UEMURA ,  Takashi OTSUKA ,  Motoji NAGATA

IPC: G09B15/02 ,  G10H1/00 ,  G10G1/00

Abstract: A musical score processing method that is realized by a computer includes receiving a control data related to displaying of a musical piece from a music processor that executes a process related to the musical piece and that is realized by a music processing program, using inter-application communication, based on a musical score processing program, and executing a display control process by displaying a musical score of the musical piece on a display device and controlling the displaying in accordance with the control data that has been received, based on the musical score processing program. The music processing program is separate from the musical score processing program.