Text ( visual ) : unmediated Speech, hearing and neural network models / by S. Nakagawa, K. Shikano, Y. Tohkura ; translated by C. Aschmann. -- : ja. -- Tokyo : Ohmsha ; Amsterdam ; Oxford : IOS Press , 1995. -- xv, 229 p. : ill ; 25 cm. -- Includes bibliographical references and index ; Translation of the original Japanese ed. "Nyuro saiensu ando tekunorojii shiriizu: Onsei chokaku to shinkeikairo-moh moderu." published by Ohmsha, 1990. -- ISBN 9051991789 ; 427490007X ; (BA26770652) ; https://ci.nii.ac.jp/ncid/BA26770652 Other Title(s): 音声・聴覚と神経回路網モデル ; Nyuro saiensu ando tekunorojii shiriizu: onsei chokaku to shinkeikairo-moh moderu. -- Author Heading(s): 中川, 聖一 ; 鹿野, 清宏 ; 東倉, 洋一 ; Aschmann, C.. -- Classification(s): DC20 : 006.3. -- Subject Heading(s): LCSH : Speech processing systems ; LCSH : Neural computers ; LCSH : Neural networks (Computer science) ; LCSH : Automatic speech recognition ; LCSH : Speech synthesis