Title:
LEARNING DEVICE, ESTIMATING DEVICE, LEARNING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2024/038560
Kind Code:
A1
Abstract:
This learning device trains a model for estimating age from voice, the learning device comprising: a converting unit that acquires converted voice converted by carrying out a voice conversion process on unconverted voice; an extracting unit that extracts a feature amount of the unconverted voice and a feature amount of the converted voice; and a learning unit that sets a correct answer age for the converted voice, thereby learning parameters of the model by using the feature amount of the unconverted voice and the feature amount of the converted voce.
More Like This:
Inventors:
KITAGISHI YUKI (JP)
MORIMOTO KENICHI (JP)
OGAWA ATSUNORI (JP)
TAWARA NAOHIRO (JP)
MORIMOTO KENICHI (JP)
OGAWA ATSUNORI (JP)
TAWARA NAOHIRO (JP)
Application Number:
PCT/JP2022/031263
Publication Date:
February 22, 2024
Filing Date:
August 18, 2022
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L25/51
Foreign References:
| US20210065733A1 | 2021-03-04 | |||
| US20220101112A1 | 2022-03-31 |
Other References:
KITAGISHI YUKI, KENICHI MORIMOTO,. TAKESHI MORI: "Introduction to speaker age estimation technology and its application to contact centers", BUSINESS COMMUNICATION, vol. 59, no. 8, 5 August 2022 (2022-08-05), pages 15 - 16, XP093140277
岡田慎太郎 他, 発話感情認識における音素事後確率を利用した表現学習とデータ拡張の評価, 電子情報通信学会技術研究報告, 29 November 2019, vol. 119, no. 321, pages 91-96, (OKADA, Shintaro et al. An evaluation of representation learning using phoneme posteriorgrams and data augmentation in speech emotion recognition. IEICE Technical Report.)
張宇涛 他, 環境音分類のための GAN による少数のラベル付きデータの拡張, 日本音響学会 2022年春季研究発表会 講演論文集 CD-ROM, 23 February 2022, pages 255-256, (ZHANG, Yutao et al. Data augmentation of few labeled samples using GAN for environmental sound classification. Reports of the 2022 spring meeting the Acoustical Society of Japan.)
犬塚雅也 他, 環境音波形の教師なしモデリング及び環境音識別のためのデータ拡張への応用, 日本音響学会 2022年春季研究発表会 講演論文集 CD-ROM, 23 February 2022, pages 297-298, (Reports of the 2022 Spring Meeting the Acoustical Society of Japan), non-official translation (INUZUKA, Masaya et al. Unsupervised modeling of environmental sound waveforms and application to data augmentation for environmental sound identification.)
岡田慎太郎 他, 発話感情認識における音素事後確率を利用した表現学習とデータ拡張の評価, 電子情報通信学会技術研究報告, 29 November 2019, vol. 119, no. 321, pages 91-96, (OKADA, Shintaro et al. An evaluation of representation learning using phoneme posteriorgrams and data augmentation in speech emotion recognition. IEICE Technical Report.)
張宇涛 他, 環境音分類のための GAN による少数のラベル付きデータの拡張, 日本音響学会 2022年春季研究発表会 講演論文集 CD-ROM, 23 February 2022, pages 255-256, (ZHANG, Yutao et al. Data augmentation of few labeled samples using GAN for environmental sound classification. Reports of the 2022 spring meeting the Acoustical Society of Japan.)
犬塚雅也 他, 環境音波形の教師なしモデリング及び環境音識別のためのデータ拡張への応用, 日本音響学会 2022年春季研究発表会 講演論文集 CD-ROM, 23 February 2022, pages 297-298, (Reports of the 2022 Spring Meeting the Acoustical Society of Japan), non-official translation (INUZUKA, Masaya et al. Unsupervised modeling of environmental sound waveforms and application to data augmentation for environmental sound identification.)
Attorney, Agent or Firm:
ITOH, Tadashige et al. (JP)
Download PDF:
Previous Patent: ELEVATOR SYSTEM
Next Patent: NETWORK INFORMATION PROCESSING DEVICE, NETWORK INFORMATION PROCESSING METHOD, AND PROGRAM
Next Patent: NETWORK INFORMATION PROCESSING DEVICE, NETWORK INFORMATION PROCESSING METHOD, AND PROGRAM