Title:
LEARNING DEVICE, ESTIMATION DEVICE, METHODS THEREFOR, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/117085
Kind Code:
A1
Abstract:
This learning device includes: a speaker vector learning unit that learns a speaker vector extraction parameter λ on the basis of at least one learning utterance sound data item in a speaker vector sound database; a non-speaker sound model learning unit that, by using a frequency component of at least one non-speaker sound data item in a non-speaker sound database, performs modelling using a probability distribution model and calculates internal parameters of the probability distribution model; and an age estimation model learning unit that extracts a speaker vector from sound data in an age estimation model learning sound database by using the speaker vector extraction parameter λ , that calculates a non-speaker sound likelihood vector from the sound data in the age estimation model learning sound database by using internal parameters μ, Σ , and that learns a parameter Ω of an age estimation model in which the speaker vector and the non-speaker sound likelihood vector are used as inputs and from which an estimated value of the age of a corresponding speaker is outputted.
Inventors:
KITAGISHI YUKI (JP)
MORI TAKESHI (JP)
KAMIYAMA HOSANA (JP)
ANDO ATSUSHI (JP)
KOBASHIKAWA SATOSHI (JP)
MORI TAKESHI (JP)
KAMIYAMA HOSANA (JP)
ANDO ATSUSHI (JP)
KOBASHIKAWA SATOSHI (JP)
Application Number:
PCT/JP2019/048049
Publication Date:
June 17, 2021
Filing Date:
December 09, 2019
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N20/00; G10L25/51
Foreign References:
| US20180308487A1 | 2018-10-25 |
Other References:
GRZYBOWSKA JOANNA, KACPRZAK STANISŁAW: "Speaker age classification and regression using i-vectors", PROC. INTERSPEECH 2016, ISCA, vol. 2016, 8 September 2016 (2016-09-08), pages 1402 - 1406, XP055833859
GHAHREMANI PEGAH, NIDADAVOLU PHANI SANKAR, CHEN NANXIN, VILLALBA JESÚS, POVEY DANIEL, KHUDANPUR SANJEEV, DEHAK NAJIM: "End-to-End Deep Neural Network Age Estimation", PROC. INTERSPEECH 2018, ISCA, vol. 2, September 2018 (2018-09-01), pages 277 - 281, XP055833861
GHAHREMANI PEGAH, NIDADAVOLU PHANI SANKAR, CHEN NANXIN, VILLALBA JESÚS, POVEY DANIEL, KHUDANPUR SANJEEV, DEHAK NAJIM: "End-to-End Deep Neural Network Age Estimation", PROC. INTERSPEECH 2018, ISCA, vol. 2, September 2018 (2018-09-01), pages 277 - 281, XP055833861
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF: