Title:
SPEECH SYNTHESIS DEVICE, SPEECH SYNTHESIS METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/112095
Kind Code:
A1
Abstract:
The purpose of the present disclosure is to prevent a decrease in the naturalness of speech while preventing the operation speed of waveform generation from being markedly harmed. Thus, the present disclosure is a speech synthesis device that generates a speech waveform in a learning phase, comprising: a waveform generation unit that obtains a speech waveform predicted value for a next time on the basis of a combination of the speech waveform and an acoustic feature quantity, as well as a state of a recurrent neural network; a conversion-to-failure-flag unit that obtains a failure flag on the basis of the speech waveform, the speech waveform predicted value, and a failure flag threshold value; a failure detection unit that obtains a failure flag predicted value on the basis of a sequence of states of the recurrent neural network and a failure detection model; a failure flag discrepancy calculation unit that calculates the discrepancy between the failure flag and the failure flag predicted value; and a failure detection model learning unit that obtains a learned failure detection model on the basis of the discrepancy and the failure detection model.
Inventors:
KANAGAWA HIROKI (JP)
Application Number:
PCT/JP2021/045878
Publication Date:
June 22, 2023
Filing Date:
December 13, 2021
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L13/047; G10L25/30
Domestic Patent References:
| WO2020136948A1 | 2020-07-02 |
Foreign References:
| JP2021067885A | 2021-04-30 | |||
| JP2021032937A | 2021-03-01 | |||
| JP2021511533A | 2021-05-06 | |||
| US20210035551A1 | 2021-02-04 | |||
| US20180336880A1 | 2018-11-22 |
Other References:
KOBAYASHI SOSUKE, UNNO YUYA, FUKUDA MASAAKI,: "Multi-task Learning of Recurrent Neural Network for Detecting Breakdowns of dialog and Language Modeling", MATERIALS OF 75TH SIG-SLUD-B502-10, 1 October 2015 (2015-10-01), pages 41 - 46, XP093071860
Attorney, Agent or Firm:
ITOH, Tadashige et al. (JP)
Download PDF: