Title:
SIGNAL PROCESSING DEVICE AND METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2022/030259
Kind Code:
A1
Abstract:
The present technology pertains to a signal processing device and method, as well as a program, for enabling reduction of content production costs. This signal processing device is provided with: a sound detection unit in which, on the basis of a mixed audio signal comprising sound of a target sound source as well as sound of a non-target sound source that is different from the target sound source, a time segment of the sound of the target sound source is detected from the mixed audio signal; and a sound determination unit for performing determination processing on whether it is easy to hear the sound of the target sound source in the mixed audio signal, on the basis of label information indicative of a time segment of the sound of the target sound source in an audio signal of the target sound source, and a detection result for the time segment of the sound of the target sound source. The present technology can be applied to signal processing devices.
More Like This:
| WO/2021/138648 | EAR-WORN ELECTRONIC DEVICE EMPLOYING ACOUSTIC ENVIRONMENT ADAPTATION |
| WO/2000/078093 | VOICE-TO-REMAINING AUDIO (VRA) INTERACTIVE HEARING AID & AUXILIARY EQUIPMENT |
| JP2009014653 | ONBOARD SYSTEM |
Inventors:
YAMAMOTO YUKI (JP)
Application Number:
PCT/JP2021/027256
Publication Date:
February 10, 2022
Filing Date:
July 21, 2021
Export Citation:
Assignee:
SONY GROUP CORP (JP)
International Classes:
G10L21/0364; G10L25/30; G10L25/48; G10L25/60
Domestic Patent References:
| WO2019027053A1 | 2019-02-07 |
Other References:
YOSUKE KOBAYASHI, KAZUHIRO KONDO: "1-Q-36 Objective Speech Intelligibility Estimation using reference signal prediction model", PROCEEDINGS OF THE 2020 SPRING MEETING OF THE ACOUSTICAL SOCIETY OF JAPAN [CD-ROM]; MARCH 16-18, 2020, 2 March 2020 (2020-03-02) - 18 March 2020 (2020-03-18), JP, pages 541 - 542, XP009534114
TAKAHASHI, HIROTO, KONDO, KAZUHIRO: "1-Q-38 On non-reference speech intelligibility estimation for degraded speech by additive noise: Evaluation of intelligibility estimation accuracy for unseen words", PROCEEDINGS OF THE 2020 SPRING MEETING OF THE ACOUSTICAL SOCIETY OF JAPAN [CD-ROM]; MARCH 16-18-2020, 2 March 2020 (2020-03-02) - 18 March 2020 (2020-03-18), JP, pages 545 - 546, XP009534115
KOBAYASHI YOSUKE; KONDO KAZUHIRO: "Japanese speech intelligibility estimation and prediction using objective intelligibility indices under noisy and reverberant conditions", APPLIED ACOUSTICS., ELSEVIER PUBLISHING., GB, vol. 156, 31 July 2019 (2019-07-31), GB , pages 327 - 335, XP085814932, ISSN: 0003-682X, DOI: 10.1016/j.apacoust.2019.07.034
TAKAHASHI, HIROTO, KONDO, KAZUHIRO: "1-Q-38 On non-reference speech intelligibility estimation for degraded speech by additive noise: Evaluation of intelligibility estimation accuracy for unseen words", PROCEEDINGS OF THE 2020 SPRING MEETING OF THE ACOUSTICAL SOCIETY OF JAPAN [CD-ROM]; MARCH 16-18-2020, 2 March 2020 (2020-03-02) - 18 March 2020 (2020-03-18), JP, pages 545 - 546, XP009534115
KOBAYASHI YOSUKE; KONDO KAZUHIRO: "Japanese speech intelligibility estimation and prediction using objective intelligibility indices under noisy and reverberant conditions", APPLIED ACOUSTICS., ELSEVIER PUBLISHING., GB, vol. 156, 31 July 2019 (2019-07-31), GB , pages 327 - 335, XP085814932, ISSN: 0003-682X, DOI: 10.1016/j.apacoust.2019.07.034
Attorney, Agent or Firm:
NISHIKAWA Takashi et al. (JP)
Download PDF: