Establishment of Vocal Communication System under Heavy Environmental Noise for Handicapped People with Speech Impediment

重环境噪声下言语障碍残疾人语音通讯系统的建立

• 批准号: 19300078
• 负责人: UCHINO Eiji
• 金额: $ 6.57万
• 依托单位: Yamaguchi University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2007
• 资助国家: 日本
• 起止时间: 2007 至 2010
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-19300078/
• 关键词: 音声変換; ソフトコンピューティング; 自己組織化マップ; 機械学習; 人工知能

The purpose of this research is to establish a vocal communication system for handicapped people with speech impediment. The system automatically converts the unclear speech of a person with a speech impediment to a clear speech by using soft computing technique. In the extraction of features of speech and the conversion of them, the model with higher conversion accuracy than ever has been accomplished, and the clear tone conversion of speech has been obtained.

本研究旨在建立一套适合有语言障碍的残障人士的语音沟通系统。该系统利用软计算技术，将语音障碍者不清晰的语音自动转换为清晰的语音。在语音特征的提取和转换中，实现了转换精度更高的模型，得到了清晰的语音声调转换。

项目成果

An RBFN-Wiener hybrid filter using higher order signal statistics

• DOI: 10.1016/j.asoc.2006.04.005
• 发表时间: 2007-06-01
• 期刊: APPLIED SOFT COMPUTING
• 影响因子: 8.7
• 作者: Suetake, Noriaki;Uchino, Eiji
• 通讯作者: Uchino, Eiji

自己組織化マップとそのツール,第10章担当(内野英治,畔津忠博)

自组织映射及其工具，第10章负责人（Eiji Uchino，Tadahiro Kutsutsu）

• 发表时间: 2008
• 作者: 大北正昭;徳高平蔵;藤村喜久郎;権田英功編
• 通讯作者: 権田英功編

A self-organizing map with twin units capable of describing a nonlinear input-output relation applied to speech code vector mapping

• DOI: 10.1016/j.ins.2007.05.028
• 发表时间: 2007-11
• 期刊: Inf. Sci.
• 作者: E. Uchino;K. Yano;T. Azetsu

Feature Extraction and Signal Reconstruction of Air and Bone Conduction Voices by Independent Component Analysis

• 发表时间: 2008-03
• 作者: T. Azetsu;E. Uchino;R. Kubota;N. Suetake

A Code Vector Conversion Model for Bone and Air Conduction Voices by Using Self-Organizing Map with Additional Learning

利用自组织映射和附加学习的骨导声和气导声的码向量转换模型

• 发表时间: 2009
• 作者: 久保田良輔;内野英治;末竹規哲;国広真実
• 通讯作者: 国広真実