Title:
A speech synthesis system, a speech synthesis method, and a voice synthesis program
Document Type and Number:
Japanese Patent JP6036681
Kind Code:
B2
Abstract:
Provided is a technology for generating rules that allow highly-natural speech synthesis without unnecessarily collecting large amount of learning data. This speech-synthesis system includes: a learning database that stores learning data, said learning data being a set of feature quantities extracted from speech waveform data; a feature-quantity-space partitioning means that partitions a feature-quantity space, which is a space related to the learning data, into subspaces; a density-detection means that detects the density of each of the subspaces into which the feature-quantity space has been partitioned and generates and outputs density information indicating said densities; and a rule-generation means that, on the basis of the outputted density information, generates speech-synthesis rules for generating pronunciation information used in speech synthesis.
Inventors:
Yasuyuki Mitsui
Reiji Kondo
Masanori Kato
Reiji Kondo
Masanori Kato
Application Number:
JP2013501129A
Publication Date:
November 30, 2016
Filing Date:
February 17, 2012
Export Citation:
Assignee:
NEC
International Classes:
G10L13/10; G10L13/06
Domestic Patent References:
JP2004117662A | 2004-04-15 | |||
JP2003271171A | 2003-09-25 | |||
JP2004117662A | 2004-04-15 | |||
JP2003271171A | 2003-09-25 |
Attorney, Agent or Firm:
Masahiko Desk
Naoki Shimosaka
Naoki Shimosaka
Previous Patent: A manufacturing method of an inspection device and a semiconductor device
Next Patent: JPS6036682
Next Patent: JPS6036682