Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LEARNING DEVICE, SPEECH SYNTHESIS SYSTEM, AND SPEECH SYNTHESIS METHOD
Document Type and Number:
WIPO Patent Application WO/2018/159403
Kind Code:
A1
Abstract:
This learning device includes: an autoregressive model that estimates a present signal from a past signal sequence and a present context label; a vocal tract feature analysis unit that analyzes an input speech signal to determine a vocal tract filter coefficient indicating a vocal tract feature; a residual signal generation unit that outputs a residual signal between the input speech signal and a speech signal predicted on the basis of the vocal tract filter coefficient; a quantization unit that quantizes the residual signal outputted from the residual signal generation unit to generate a quantized residual signal; and a learning control unit that, regarding the input speech signal corresponding to a known input text, provides, as a condition, a context label of the known input text to the autoregressive model, and associates the present context label and the past quantized residual signal sequence regarding the input speech signal with the present quantized residual signal, thereby performing learning of the autoregressive model.

Inventors:
TACHIBANA KENTARO (JP)
TODA TOMOKI (JP)
Application Number:
PCT/JP2018/006166
Publication Date:
September 07, 2018
Filing Date:
February 21, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NAT INST INF & COMM TECH (JP)
International Classes:
G10L13/06; G10L13/10; G10L19/06
Domestic Patent References:
WO2009022454A12009-02-19
Foreign References:
JPH03269599A1991-12-02
Other References:
KANEKO, TAKUHIRO ET AL.: "Generative Adversarial Network- based Postfiltering for Statistical Parametric Speech Synthesis", IEICE TECHNICAL REPORT, vol. 116, no. 378, 13 December 2016 (2016-12-13), pages 89 - 94, ISSN: 0913-5685
Attorney, Agent or Firm:
FUKAMI PATENT OFFICE, P.C. (JP)
Download PDF: