Processing

Please wait...

Settings

Settings

Goto Application

1. WO2013008384 - SPEECH SYNTHESIS DEVICE, SPEECH SYNTHESIS METHOD, AND SPEECH SYNTHESIS PROGRAM

Publication Number WO/2013/008384
Publication Date 17.01.2013
International Application No. PCT/JP2012/003760
International Filing Date 08.06.2012
IPC
G10L 13/06 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
06Elementary speech units used in speech synthesisers; Concatenation rules
G10L 13/08 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
08Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
CPC
G10L 13/08
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
08Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
G10L 15/08
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
G10L 2013/105
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
08Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
10Prosody rules derived from text; Stress or intonation
105Duration
Applicants
  • 日本電気株式会社 NEC Corporation [JP]/[JP] (AllExceptUS)
  • 三井 康行 MITSUI, Yasuyuki [JP]/[JP] (UsOnly)
  • 加藤 正徳 KATO, Masanori [JP]/[JP] (UsOnly)
  • 近藤 玲史 KONDO, Reishi [JP]/[JP] (UsOnly)
Inventors
  • 三井 康行 MITSUI, Yasuyuki
  • 加藤 正徳 KATO, Masanori
  • 近藤 玲史 KONDO, Reishi
Agents
  • 岩壁 冬樹 IWAKABE, Fuyuki
Priority Data
2011-15284911.07.2011JP
Publication Language Japanese (JA)
Filing Language Japanese (JA)
Designated States
Title
(EN) SPEECH SYNTHESIS DEVICE, SPEECH SYNTHESIS METHOD, AND SPEECH SYNTHESIS PROGRAM
(FR) DISPOSITIF DE SYNTHÈSE DE LA PAROLE, PROCÉDÉ DE SYNTHÈSE DE LA PAROLE ET PROGRAMME DE SYNTHÈSE DE LA PAROLE
(JA) 音声合成装置、音声合成方法および音声合成プログラム
Abstract
(EN)
Provided are a speech synthesis device, a speech synthesis method, and a speech synthesis program, wherein it is possible to represent a phoneme at a duration that is shorter than the duration when the phoneme was modeled by means of a statistical method. This speech synthesis device (80) is provided with a phoneme boundary updating means for updating the phoneme boundary position which is the boundary between a phoneme modeled by means of a statistical method and another phoneme adjacent to the aforementioned phoneme by using a voiced index which is an index indicating the degree to which each state representing the phoneme is voiced.
(FR)
La présente invention concerne un dispositif de synthèse de la parole, un procédé de synthèse de la parole et un programme de synthèse de la parole qui permettent de représenter un phonème avec une durée qui est plus courte que la durée obtenue lorsque le phonème a été modélisé au moyen d'un procédé statistique. Ce dispositif de synthèse de la parole (80) est équipé d'un moyen de mise à jour de frontière de phonèmes servant à la mise à jour de la position de la frontière de phonèmes qui est la frontière entre un phonème modélisé au moyen d'un procédé statistique et un autre phonème adjacent au phonème susmentionné en utilisant un indice voisé qui est un indice indiquant le degré auquel chaque état représentant le phonème est voisé.
(JA)
 統計的手法によりモデル化された場合の継続時間長よりも短い継続時間長で音素を表現できる音声合成装置、音声合成方法および音声合成プログラムを提供する。本発明による音声合成装置80は、統計的手法によりモデル化された音素を表現する各状態の有声らしさの度合いを示す指標である有声性指標を用いて、その音素に隣接する他の音素との境界である音素境界位置を更新する音素境界更新手段81を備えている。
Also published as
Latest bibliographic data on file with the International Bureau