公开(公告)号：US11653167B2

公开(公告)日：2023-05-16

申请号：US16841953

申请日：2020-04-07

Applicant: Sony Interactive Entertainment Inc.

Inventor： Fabio Cappello ,  Marina Villanueva-Barreiro ,  Oliver Hume

IPC: H04S7/00 ,  H04S3/00 ,  G06N20/00 ,  G10H1/00 ,  G10L15/06 ,  G10L15/08

CPC classification number: H04S7/303 ,  G06N20/00 ,  G10H1/0008 ,  G10L15/063 ,  G10L15/083 ,  H04S3/008 ,  G10H2210/056 ,  G10H2210/086 ,  G10L2015/088 ,  H04S2400/01 ,  H04S2400/11

Abstract: A system for generating audio content in dependence upon an input audio track comprising audio corresponding to one or more sound sources, the system comprising an audio input unit operable to input the input audio track to one or more models, each representing one or more of the sound sources, and an audio generation unit operable to generate, using the one or more models, one or more audio tracks each comprising a representation of the audio contribution of the corresponding sound sources of the input audio track, wherein the generated audio tracks comprise one or more variations relative to the corresponding portion of the input audio track.

公开(公告)号：US11528577B2

公开(公告)日：2022-12-13

申请号：US16875115

申请日：2020-05-15

Applicant: Sony Interactive Entertainment Inc.

Inventor： Fabio Cappello ,  Marina Villanueva-Barreiro ,  Oliver Hume

IPC: H04S7/00 ,  G06T17/00 ,  G06V40/16 ,  H04R1/40 ,  G01S5/16

Abstract: A method of obtaining a head-related transfer function for a user is provided. The method comprises generating an audio signal for output by a handheld device and outputting the generated audio signal at a plurality of locations by moving the handheld device to those locations. The audio output by the handheld device is detected at left-ear and right-ear microphones. A pose of the handheld device relative to the user's head is determined for at least some of the locations. One or more personalised HRTF features are then determined based on the detected audio and corresponding determined poses of the handheld device. The one or more personalised HRTF features are then mapped to a higher-quality HRTF for the user, wherein the higher-quality HRTF corresponds to an HRTF measured in an anechoic environment. This mapping may be learned using machine learning, for example. A corresponding system is also provided.

公开(公告)号：US20220148584A1

公开(公告)日：2022-05-12

申请号：US17452499

申请日：2021-10-27

Applicant: Sony Interactive Entertainment Inc.

Inventor： Fabio Cappello ,  Danjeli Schembri ,  Oliver Hume

IPC: G10L15/187 ,  G06F40/279 ,  G10L15/10 ,  G11B27/02

Abstract: A data processing apparatus includes storage circuitry to store audio data for a plurality of respective dialogue recordings for a content and to store text data indicative of a sequence of respective words within the audio data for each of the plurality of respective dialogue recordings, analysis circuitry to compare the text data for a current dialogue recording with predetermined text data for the content and to output comparison data for the current dialogue recording, the comparison data indicative of one or more differences between the text data for the current dialogue recording and the predetermined text data, selection circuitry to select one or more candidate dialogue recordings from the plurality of respective dialogue recordings for the content in dependence upon the comparison data, and recording circuitry to modify at least a portion of the audio data for the current dialogue recording in dependence upon the audio data for one or more of the candidate dialogue recordings to obtain modified audio data and to store the modified audio data for the current dialogue recording.

公开(公告)号：US20220111294A1

公开(公告)日：2022-04-14

申请号：US17498947

申请日：2021-10-12

Applicant: Sony Interactive Entertainment Inc.

Inventor： Marina Villanueva Barreiro ,  Michael Lee Jones ,  Oliver Hume ,  Fabio Cappello ,  Danjeli Schembri

IPC: A63F13/54 ,  G06F40/20 ,  G10L15/16 ,  G10L15/22 ,  G10L25/60 ,  G10L25/30

Abstract: A data processing apparatus includes input circuitry to receive audio data for a plurality of respective dialogue recordings for a video game, classification circuitry comprising one or more machine learning models to receive at least a portion of the audio data for each dialogue recording and trained to output classification data indicative of a quality classification of a dialogue recording in dependence upon one or more properties of the audio data for the dialogue recording, and storage circuitry to store identification data for one or more of the plurality of dialogue recordings in dependence upon the classification data.

公开(公告)号：US20220062770A1

公开(公告)日：2022-03-03

申请号：US17408684

申请日：2021-08-23

Applicant: Sony Interactive Entertainment Inc.

Inventor： Fabio Cappello ,  Maria Chiara Monti ,  Matthew Sanders ,  Timothy Bradley ,  Oliver Hume ,  Jason Craig Millson

IPC: A63F13/63 ,  A63F13/86 ,  A63F13/215 ,  G10L15/197

Abstract: A content generation system, the system comprising an input obtaining unit operable to obtain one or more samples of input text and/or audio relating to a first content, an input analysis unit operable to generate n-grams representing one or more elements of the obtained inputs, a representation generating unit operable to generate a visual representation of one or more of the generated n-grams, and a display generation unit operable to generate second content comprising one or more elements of the visual representation in association with the first content.

公开(公告)号：US20210124996A1

公开(公告)日：2021-04-29

申请号：US17074827

申请日：2020-10-20

Applicant: Sony Interactive Entertainment Inc.

Inventor： Mark Jacobus Breugelmans ,  Oliver Hume ,  Fabio Cappello ,  Nigel John Williams

IPC: G06K9/62 ,  H04N1/44 ,  G06F21/62

Abstract: An encoding apparatus is provided. The apparatus comprises an input unit operable to obtain a plurality of training images, said training images being for use in training a machine learning model. The apparatus also comprises a label unit operable to obtain a class label associated with the training images; and a key unit operable to obtain a secret key for use in encoding the training images. The apparatus further comprises an image noise generator operable to generate, based on the obtained secret key, noise for introducing into the training images. The image noise generator is configured to generate noise that correlates with the class label associated with the training images such that a machine learning model subsequently trained with the modified training images learns to associate the introduced noise with the class label for those images. A corresponding decoding apparatus is also provided.

公开(公告)号：US20210050023A1

公开(公告)日：2021-02-18

申请号：US16985310

申请日：2020-08-05

Applicant: Sony Interactive Entertainment Inc.

Inventor： Oliver Hume ,  Fabio Cappello ,  Marina Villanueva-Barreiro ,  Michael Lee Jones

IPC: G10L19/008 ,  G10L19/16 ,  H04S3/00

Abstract: A system for determining prioritisation values for two or more sounds within an audio clip includes: a feature extraction unit operable to extract characteristic features from the two or more sounds, a feature combination unit operable to generate a combined mix comprising extracted features from the two or more sounds, an audio assessment unit operable to identify the contribution of one or more of the features to the combined mix, a feature classification unit operable to assign a saliency score to each of the features in the combined mix, and an audio prioritisation unit operable to determine relative priority values for the two or more sounds in dependence upon the assigned saliency scores for each of one or more features of the sounds.

公开(公告)号：US20200179806A1

公开(公告)日：2020-06-11

申请号：US16701730

申请日：2019-12-03

Applicant: Sony Interactive Entertainment Inc.

Inventor： Hogarth Andall ,  Oliver Hume

IPC: A63F13/537 ,  A63F13/35

Abstract: A method of determining user engagement in a game includes: receiving data from a plurality of remote entertainment devices at a server, the data from a respective entertainment device associating at least a first feature state of the game with an action by a user of that respective entertainment device indicative of a predetermined degree of engagement by the user with the game, aggregating the data received from the plurality of entertainment devices, and determining a level of correspondence between one or more feature states and user actions indicative of the predetermined degree of engagement.

公开(公告)号：US10462598B1

公开(公告)日：2019-10-29

申请号：US16282400

申请日：2019-02-22

Applicant: Sony Interactive Entertainment Inc.

Inventor： Marina Villanueva-Barreiro ,  Oliver Hume ,  Scott Wardle

IPC: H04S7/00 ,  G10L21/02 ,  H04R5/04

Abstract: A system for generating a head-related transfer function, HRTF, for a given position with respect to a listener, the system comprising a dividing unit operable to divide each of a plurality of existing HRTFs, each corresponding to a respective plurality of positions, into first and second components, an interaural time difference determination unit operable to determine an interaural time difference expected by a user for a sound source located at the given position in dependence upon the respective first components, an interpolation unit operable to generate an interpolated second component by interpolating generated second components using a weighting dependent upon the respective positions for the corresponding HRFTs and the given position, and a generation unit operable to generate an HRTF for the given position in dependence upon the interaural time difference and the interpolated second component.

公开(公告)号：US12282590B1

公开(公告)日：2025-04-22

申请号：US18317253

申请日：2023-05-15

Applicant: Sony Interactive Entertainment Inc.

Inventor： Matthew Sanders ,  Richard Downey ,  Oliver Hume ,  Michael Karl Werle

IPC: G06F3/01 ,  A63F13/21 ,  A63F13/24

Abstract: A user input device includes an optical window facing onto a region of skin of the user when the user input device is in normal use, a monochromatic light source arranged to emit light through the optical window, a spectral dispersal unit adapted to disperse the spectrum of light reflected back from the region of skin of the user, the reflected light no longer being wholly monochromatic due to Raman scattering, and a light sensor operable to detect at least some of the dispersed spectrum of light and output corresponding light data.