Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
【発明の名称】音声認識用単語辞書作成装置及び連続音声認識装置
Document Type and Number:
Japanese Patent JP2974621
Kind Code:
B2
Abstract:
PROBLEM TO BE SOLVED: To cope with deformation in voice utterance in longer contexts and to greatly improve word recognization rate. SOLUTION: Based on the data of vocal feature parameters extracted from the voice signals of a vocalized sentence and the phoneme mark series started to be written correspondingly to it, a pronounciation network preparing device 20 prepares a pronounciation network by learning the pronounciation network composed from a neural network using the results of pattern matching including substitution, dropout, and insertion of phonemes as learning data. A word dictionary preparing device 50 registers the vocal mark series obtained by executing the processing in which the maximum output value is obtained from the output layer when inputting the input phoneme mark series in reference with the pronounciation network based on the input phoneme mark series to the input layer of the pronounciation network for the input phoneme mark series as a voice recognizing word dictionary.

Inventors:
KOSAKA YOSHINORI
Application Number:
JP24763196A
Publication Date:
November 10, 1999
Filing Date:
September 19, 1996
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
EI TEI AARU ONSEI HONYAKU TSUSHIN KENKYUSHO KK
International Classes:
G06F15/18; G06N3/00; G10L15/06; G10L15/08; G10L15/10; G10L15/16; G10L15/18; G10L15/183; G10L15/22; G10L17/06; (IPC1-7): G10L3/00; G10L3/00; G06F15/18
Domestic Patent References:
JP6289894A
JP5188998A
JP9198083A
Other References:
日本音響学会平成6年度秋季研究発表会講演論文集▲I▼ 1−R−11「発音変形ルールの自動生成に基づく音声認識辞書のマルチエントリー化」p.213−214(平成6年11月1日国会図書館受入)
日本音響学会平成8年度秋季研究発表会講演論文集▲I▼ 2−3−13「音素タイプライタ出力効果を用いた発音ネットワークの構築」p.73−74(平成8年9月25日発行)
電子情報通信学会技術研究報告[言語理解とコミュニケーション]Vol.96,No.419,NLC96−40,「発音ネットワークに基づく発音辞書の自動生成」p.15−22(1996/12/12)
電子情報通信学会技術研究報告[音声]Vol.95,No.123,SP95−30,「複数音素にわたるHMMの誤認識特性を用いた語彙候補の追加」p.41−47(1995/6/23)
電子情報通信学会技術研究報告[音声]Vol.96,No.421,SP96−71,「発音ネットワークに基づく発音辞書の自動生成」p.15−22(1996/12/12)
電子情報通信学会論文誌 Vol.J79−D▲II▼ No.12「複数音素にまたがる誤認識特性を用いた音素候補系列追加モデル」p.2086−2095(平成8年12月25日発行)
電子情報通信学会論文誌 Vol.J80−D−▲II▼ No.10「発音ネットワークに基づく発音辞書の自動生成」p.2626−2635(平成9年10月25日発行)
Attorney, Agent or Firm:
Aoyama Ryo (2 outside people)