Title:
音声合成装置及び方法
Document Type and Number:
Japanese Patent JP3614874
Kind Code:
B2
Abstract:
PURPOSE:To generate a synthesized voice, which has no sense of incongruity compared with an actual human voice, by normalizing spectrum envelope loci of voice unit data to be used for voice synthesis. CONSTITUTION:The device is provided with a voice synthesis rule section 4 which generates a rhythm information by a prescribed phoneme rule and a rhythm rule based on phoneme symbols and rhythm symbols and a voice synthesis section 5 which generates synthesized voices based on the voice unit that stores required number of frames of unique characteristic parameters as synthesis units and a rhythm information. Moreover, a voice unit storage section 2, which sets a typical characteristic parameter in connecting frames between voice units against at least one phoneme and stores voice units in which spectrum envelope loci are normalized by typical feature parameters, is provided. During the synthesis of an arbitrary voice, a voice unit data set, in which spectrum envelope loci stored in the section 2 are normalized, is used.
More Like This:
JP2003005776 | VOICE SYNTHESIZING DEVICE |
WO/1999/012324 | NATURAL LANGUAGE COLLOQUY SYSTEM SIMULATING KNOWN PERSONALITY ACTIVATED BY TELEPHONE CARD |
JPH08129398 | TEXT ANALYSIS DEVICE |
Inventors:
Keiichi Yamada
Yoshiaki Oikawa
Yoshiaki Oikawa
Application Number:
JP22815793A
Publication Date:
January 26, 2005
Filing Date:
August 19, 1993
Export Citation:
Assignee:
ソニー株式会社
International Classes:
G10L13/02; G10L13/06; G10L13/07; (IPC1-7): G10L13/08; G10L13/06
Domestic Patent References:
JP310300A | ||||
JP3208100A |
Attorney, Agent or Firm:
Keiki Tanabe