| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a system for processing an audio data, which enables a user to generate and output various types of documents by only making the voice recognized. <P>SOLUTION: The system for processing the audio data, comprising; a processing command / data recognition unit 105 for recognizing the processing command in the documents, wherein languages (processing commands) showing document style, character color, character size, character type, and line feed are input into an audio recognition unit 101 or an audio data input unit 102, while a language representing a content for an output document is also input into both units; a processing command recognition unit 106 for responding to the processing command; a command processing unit 114 for processing the processing command; and an output unit 108 for outputting a document, which is processed, by using the processing commands of the document style, the character color, the character size, the character type, and the line feed. <P>COPYRIGHT: (C)2005,JPO&NCIPI |
