Title:
ELECTRONIC DEVICE AND PERSONALIZED TEXT-TO-SPEECH MODEL GENERATION METHOD BY ELECTRONIC DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/196925
Kind Code:
A1
Abstract:
According to various embodiments, an electronic device may comprise a memory including instructions and a processor for executing the instructions, wherein when the instructions are executed by the processor, the processor: records a user's speech corresponding to a text so as to acquire recorded data in which the text and the user's speech are matched; while training a speech model in order to generate a personalized text-to-speech model corresponding to the user, stores the speech model, having been trained on the basis of part of the recorded data, as an intermediate model; generates an intermediate result according to the training by using the intermediate model and provides the intermediate result to the user; and receives the user's feedback with regard to the intermediate result. Various other embodiments may be possible.
Inventors:
SUNG JUNESIG (KR)
KIM KWANGHOON (KR)
PARK HYOUNGMIN (KR)
KIM KWANGHOON (KR)
PARK HYOUNGMIN (KR)
Application Number:
PCT/KR2022/001191
Publication Date:
September 22, 2022
Filing Date:
January 24, 2022
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G10L13/08; G10L13/027; G10L15/06; G10L25/78; G11B20/10
Foreign References:
KR20190104269A | 2019-09-09 | |||
KR20190085882A | 2019-07-19 | |||
KR20200145776A | 2020-12-30 | |||
US20210074261A1 | 2021-03-11 | |||
US10839809B1 | 2020-11-17 |
Attorney, Agent or Firm:
MUHANN PATENT & LAW FIRM (KR)
Download PDF: