JP2003167600A5

JP2003167600A5 -

Info

Publication number: JP2003167600A5
Application number: JP2001370354A
Authority: JP
Filing date: 2001-12-04
Publication date: 2005-07-14
Anticipated expiration: 2021-12-04

Claims

Obtaining means for obtaining more recognition result candidates to recognize the voice input,
Recognition result for each candidate acquired by the acquiring means, and determining means for determining a display mode for displaying on the display means,
Display control means for controlling to display the recognition result candidates based on the display mode determined by the determining means;
Speech recognition apparatus comprising: a.

The acquisition means further acquires a recognition score when the voice is recognized,
The speech recognition apparatus according to claim 1, wherein the determination unit determines the display mode based on the recognition score.

The speech recognition apparatus according to claim 1, wherein the determination unit determines the display mode based on an attribute of the recognition result candidate.

The attribute is at least one of the importance of the recognition result candidate vocabulary, the part of speech, the process selection command, the information search keyword, the frequency used , and the language type. The speech recognition apparatus according to claim 3, wherein

The determination means, as the display mode, is at least any one of a graphic user interface type, an arrangement, a display position, a size, a display color, a display shape , and a font of characters to be displayed when displaying individual recognition result candidates. The speech recognition apparatus according to claim 1, wherein:

User speech recognition apparatus according to claim 1, further comprising a display mode setting means capable of setting a procedure for determining the display mode.

The display control means controls to display the recognition result candidates in a selectable manner,
According recognition result candidates selected from been recognition result candidates displayed by said display control means, characterized in that it further comprises control means for processing corresponding to the recognition result candidate is controlled to be executed in its own device or the external device The speech recognition apparatus according to claim 1 .

A page description language display device that displays a display screen based on input data in a predetermined page description language format,
An acquisition means for acquiring a recognition result candidate by recognizing an input voice when the predetermined page description language format data includes a predetermined identifier instructing voice recognition;
And page description data generating means for generating data of a page description language for displaying the recognition result candidate graphical user interface display mode is determined for each (GUI),
A page description language display device comprising:

An acquisition step of acquiring more recognition result candidates to recognize the voice input,
For each acquired recognition result candidate, a determining step for determining a display mode when displaying on the display means ;
A display control step for controlling to display the recognition result candidates based on the determined display mode;
Speech recognition method, characterized in that it comprises a.

The acquisition step further acquires a recognition score when the voice is recognized,
The speech recognition method according to claim 9, wherein the determining step determines the display mode based on the recognition score.

The determination step, the recognition results based on the attribute of the candidate, the speech recognition method of claim 9, wherein the determining the display mode.

The attribute is at least one of the importance of the recognition result candidate vocabulary, the part of speech, the process selection command, the information search keyword, the frequency used , and the language type. speech recognition method of claim 11, wherein a is or.

In the determination step , as the display mode, at least any one of a graphic user interface type, an arrangement, a display position, a size, a display color, a display shape, and a character font to be displayed when displaying individual recognition result candidates speech recognition method of claim 9, wherein the determining.

The speech recognition method according to claim 9, further comprising a display mode setting step in which a user can set a procedure for determining the display mode.

The display control step performs control so that the recognition result candidate is selectably displayed,
According to the recognition result candidate selected from the recognition result candidates displayed in the display control step, the method further includes a control step of controlling the processing corresponding to the recognition result candidate to be executed in the own device or an external device. The speech recognition method according to claim 9.

A page description language display method for displaying a display screen based on input data in a predetermined page description language format,
An acquisition step of acquiring a recognition result candidate by recognizing an input voice when the predetermined page description language format data includes a predetermined identifier instructing voice recognition;
And page description data generating step of generating data of a page description language for displaying the recognition result candidate graphical user interface display mode is determined for each (GUI),
A page description language display method characterized by comprising :

A program for causing a computer to execute the speech recognition method according to claim 9 .

A program for causing a computer to execute the page description language display method according to claim 16 .

A computer-readable storage medium storing the program according to claim 17 or 18.