JPS62106573A - Electronic dictionary device - Google Patents

Abstract

PURPOSE:To facilitate the input of headwords by inputting the head word required to be retrieved in voices and not only displaying the retrieved illustration text on a display device but outputting it in voices. CONSTITUTION:An operator inputs a desired headword B retrieved out of a table registered previously in voices through a microphone 11. These voices are converted into electric signals and then into a sound signal A. A voice parameter signal P is extracted out of a sound signal D undergone the digital conversion. The signal P is compared successively with the voice parameters stored in a parameter table 23 by a discriminator 24. The headword B is recognized when the coincidence is obtained between both voice parameters. The headword B thus inputted in voices is recognized as the desired headword B and inputted to a directory 13. A file device 14 displays a character illustration text 15 or the contents of a picture graphic illustration text on a displaying- device 17 according to a file number C outputted from the directory 13. While the contents of a voice illustration text 16 are delivered in voices as necessary through a speaker 18.

Description

[Detailed Description of the Invention] [Industrial Application Field] This invention relates to an electronic dictionary device that allows entry of headwords by voice and knowing the contents of explanatory text by letters, pictures, or voice. .

[Prior Art] FIG. 3 is a block diagram showing a conventional electronic dictionary device including an editor of a computer, a help function of an electronic manual, and the like. In the figure, (1) is a keyboard as an input device, (2) is a directory that associates headwords (1a) input from keyboard (1) with file numbers (2a), and (3) is from directory (2). Explanation text (3) corresponding to the input file number (2a)
(a) is a file device in which the collection is stored, and (4) is a display device that displays the contents of the explanatory text (3a) retrieved from the file device (3) as characters and images (4a).

Next, the operation of the conventional device shown in Section 3 will be explained. The desired headword (1) entered on the keyboard (1)
The character string in a) is input to the directory (2), and the character string in the directory (2) is input as a headword file number correspondence table.
) is converted into a file number (2a) for searching for the desired explanatory text. When the file number (2a) is input, the file device (3) searches for the explanatory text (3a) corresponding to the file number (2a) and selectively outputs the desired explanatory text (3a). File device (3
The contents of the explanatory text) 13a) read from ) are displayed as characters or images fi (4a) on a predetermined header of the display device (4>).

[Problems to be Solved by the Invention] As described above, the conventional electronic dictionary device operated manually on a computer inputs headwords one character at a time on the keyboard (one
), there was a problem in that it was time-consuming, especially when inputting words such as Japanese that included katakana and kanji. In addition, since the only output device for search results is a display device (4), if the content of the explanatory text (3a) is like a dictionary, it will take 3 effort to read, and it will cause damage to eyesight.
However, there was a problem in that it did not have any impact.

This invention was made to solve the above-mentioned problems, and it is possible to enter the headword to be searched by voice, and the searched explanatory text is not only displayed on the display device but also outputted by voice. The purpose is to obtain an electronic dictionary device that can be used.

[Means for Solving the Problems] The electronic dictionary device according to the present invention includes a voice recognition mechanism that recognizes an input audio signal as a headword, a directory that outputs a file number corresponding to the headword, and a file number The system is equipped with a file device for selecting an explanatory text according to the instructions, a display device for displaying the contents of the explanatory text, and an audio output mechanism for outputting audio.

[fl: Use In this invention, the voice recognition mechanism recognizes the voice emitted by the operator as a headword, the directory converts the headword into a file number, and selects explanatory text in the file device according to the file number. The content of the desired explanatory text is displayed on the display device as characters or images, and the audio output mechanism outputs audio.

[Example] Hereinafter, a second embodiment of the present invention will be described. 1st
The figure is a block diagram showing an embodiment of the invention. In Fig. 1, (11) is a microphone that outputs an audio signal Af according to the input audio, and (12) is a microphone that outputs an audio signal Af according to the input audio, and (12) is a microphone that outputs an audio signal Af according to the input audio, and (12) when an audio signal A is input from (11), the audio signal A is used as a headword B. It is a speech recognition mechanism that recognizes speech. (13) is a directory into which the headword B is input from the speech recognition mechanism (12), and the file number C corresponding to the headword B is output.

(14) is file number C from directory (13)
is the input file device, and the explanatory text of the multimedia format corresponding to file number C is kana,
Character explanation text consisting of character codes including kanji (15
) and a collection of audio explanatory texts (16) that are compressed and encoded audio waveforms when the explanatory text is read by a woman.

The file device (14) is also provided with image figure description text (not shown) consisting of pixel sets or vector sets. The file numbers C corresponding to these explanatory texts (15) and (16) are all located in the directory (13).
It has been posted on S.

(17) is a display device that displays the contents of the character explanation text (15), and (18) is a voice 21! This is a speaker serving as an audio output mechanism for audio outputting the contents of the clear text (16). (19) is an audio conversion device that is installed between the file device W (14) and the speaker (18) as needed, and converts the content of the text explanation text (15) into audio. and is output to a speaker (18). P4 equipped with a voice conversion/synthesis device (19),
Since the content of the text explanation text (15) can be directly output as audio, it can be abbreviated as audio explanation text (16>), but both explanation texts (15) and (16) may be used together for audio output. .

Also, Figure 2 shows the voice recognition mechanism (12) and the directory (
13), in which (Zl) is a converter that converts the analog audio signal A into a digital audio signal, and (22) is a converter that converts the analog audio signal A into a digital audio signal. A feature extractor (23) filters and analyzes the voice signal obtained by filtering it and extracts a voice parameter signal P; 24) compares the audio parameter signal P with the audio parameters in the parameter table (23) and determines the headword B.
This is a discriminator that recognizes.

These (21) to (24) create a speech recognition mechanism (12).
is configured.

(Z5) is a heading register registered corresponding to headword B. When headword B is input, each file number (26) to (29) corresponding to this is specified, and these are registered as file numbers. It is designed to be output as C to the file device (14). (26) is the file number in which the structure of the explanatory text and its output format are written, (27
) is the file number corresponding to the character explanation text 1 to (15), (28) is the file number corresponding to the audio explanation text (16), and (29) is the image figure file number corresponding to the image figure explanation text. These (25) ~ (Z
Directory (2) is composed of a plurality of sets of correspondence tables shown in 9).

Next, the operation of the embodiment of the present invention will be described with reference to FIGS. 1 and 2.

First, the operator enters the headword B of the item to be searched for from the pre-registered table into the microphone (11) by voice. This voice is converted into an electrical signal and becomes the voice signal A, which is sent to the ^D converter (21) in the voice recognition mechanism (12).
), in the feature extractor (22),
A voice parameter signal P is extracted from the audio signal digitally converted by the D converter (21). The voice parameter signal P is determined by a discriminator (24) into a parameter table (
23), and when they match, it is recognized as headword B.

The headword B input by voice in this way is recognized as the headword B of the item you want to search, and
is input. The headword register (25) in the directory (13) contains file numbers (27) to (29) corresponding to the text portion, audio sentence portion, and image graphics portion of the explanation table specified by one headword B. and the file number (26) that determines the output format at the same time,
Since each part is individually registered in the file device (14), each code (26) to (29) may be individually designated. According to the file number C output from the directory (13), the file device (14) displays the contents of the character explanation text (15) or the image/figure explanation text I on the display device (17), and also provides an audio explanation as appropriate. Text (1
The contents of step 6) are output as audio through the speaker (18). In addition, if the audio explanation text (16) is omitted, the content of the character explanation text (15) is converted to the audio conversion/synthesis device ff (
After converting into an output equivalent to the voice explanation text (16) in step 19), the voice is outputted by the speaker (18).

The electronic dictionary device W according to the embodiment of the present invention described above has a multi-functionality by providing a voice recognition mechanism (12), a file device such as a fixed disk (4), a display device (17), and a microprocessor. It can be realized compactly as a personal computer or workstation.

[Invention (effect)] As described above, according to the present invention, the voice recognition M1 side that recognizes input audio signals as headwords, the directory that outputs the file number corresponding to the headword, and the explanation according to the file number. A file device for retrieving text, a display device for displaying the contents of explanatory text 1~, and a voice output mechanism for outputting voice are provided, and the headword to be searched can be inputted by voice, and the headword to be searched can be inputted by voice. An electronic dictionary device is obtained in which the explanatory text I is not only displayed on a display device but also outputted in voice, thereby making it easier to input headwords, reducing labor at the time of outputting, and eliminating adverse effects on visual acuity. It has the effect of

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is a block diagram showing the voice recognition mechanism shown in FIG. It is a diagram. (11)...Microphone (12)...Speech recognition mechanism (13)...Directory (14)...
File device<15)...Character explanation text (16)...Voice explanation text (17)...Display device (18)...Speaker (19)...Audio conversion device (21) ... ΔD converter (22) ... Feature extractor (23) ... Parameter table (24) ... Discriminator A ... Audio No. 18 B
...Headword C...File number P...
Audio parameter signal In the figures, the same reference numerals indicate the same or corresponding parts. Flood 1 figure 18, stripe 6-frame 2 figure P: 8 meters b sumarame-2 b total

Claims (5)

[Claims] (1) A voice recognition mechanism that recognizes an input audio signal as a headword, a directory that outputs a file number corresponding to the headword, a file device that selects an explanatory text according to the file number, and a file device that selects an explanatory text according to the file number; An electronic dictionary device comprising a display device for displaying content and a voice output mechanism for outputting voice. (2) The electronic device according to claim 1, wherein the explanatory text includes at least a written explanatory text and an audio explanatory text, and the audio output mechanism includes a speaker that outputs the content of the audio explanatory text. Dictionary device. (3) The electronic dictionary device according to claim 1 or 2, wherein the voice output mechanism includes a voice conversion/synthesis device that converts and synthesizes the contents of the explanatory text into voice and outputs the same. (4) The speech recognition mechanism includes a feature extractor that extracts a speech parameter signal from a speech signal, a parameter table that holds speech parameters corresponding to all headwords registered in the directory, and the speech parameter signal and the speech The method according to any one of claims 1 to 3 is characterized in that it has a discriminator that outputs a headword by comparing it with a parameter, and adopts a speaker-independent word recognition method. Electronic dictionary device. (5) The electronic dictionary device according to claim 1, wherein the explanation text includes image/figure explanation text in addition to text explanation text and audio explanation text.