Short-utterance recognition builder

Prev Next

Available in Classic and VPC

Using the CLOVA Speech Builder, you can request and manage speech recognition tasks through a UI environment. Builders are provided per domain, and you can use the following menus within the Builder:

  • Demo menu: Register and manage recognition tasks, edit results, and export output
  • Keyword Boosting menu: Register keywords for words you want to boost in recognition probability, and manage registered keywords
  • Recognition Result Correction menu: Post-process recognition results to correct them
  • Settings menu: View domain information
Note

Some features may not be displayed depending on the domain type.

Launch the Builder

To run the Builder:

Note

You must create a domain before using the Builder. For more information, see Create a domain.

  1. From the NAVER Cloud Platform console, navigate to i_menu > Services > AI Services > CLOVA Speech.
  2. Click the Domain menu for the short-utterance recognition type.
  3. Click [Launch Builder] button for the domain you want to use.

Demo

In the Builder's Demo menu, you can use the short-utterance recognition demo by uploading audio directly through the NAVER Cloud Platform console without integrating API Gateway. You can view the recognition result on the screen and download it. A CLOVA Speech 1-time call fee is charged when a recognition attempt is made.
The Demo screen is structured as follows:

clovaspeech-builder_keyword_ko

Component Description
① Menu name Shows the current menu name.
② Select language Select the recognition language (Korean, English, Japanese, Chinese).
③ Upload window Audio upload area.
④ Recognition result Speech recognition result; download available.
⑤ Pronunciation evaluation result Word- and sentence-level pronunciation evaluation results.
Note
  • Pronunciation evaluation is available only when the language is set to Korean or English.
  • If any word receives a pronunciation score below 0.7, the word is underlined. Hover over the word to view detailed evaluation results.

To use CLOVA Speech features in the console without integrating API Gateway, upload the audio file by dragging and dropping it into the upload window, or click the window to select a file. The following upload file requirements must be checked when uploading:

  • Audio file upload requirements
    • Size: 10 MB or less
      • Format: Audio files such as mp3, aac, ac3, ogg, flac, wav
    • Audio length: 60 seconds or less

Keyword Boosting

Keyword boosting allows you to increase recognition accuracy for specific words. In the Keyword Boosting menu, you can register and manage keywords.

Keyword Boosting Screen

The basic layout of the Keyword Boosting menu is as follows:
clovaspeech-builder_keyword_ko

Component Description
① Menu name Shows the current menu name.
② Register keywords Deploy keywords to the server.
③ Keyword management features Upload keyword files, download registered keywords, delete keywords.
④ Search box Search keywords.
⑤ Keyword list List of registered keywords.

Register keywords

To register added keywords on the server:

  1. Add your keywords.
    • Register the keywords in the keyword input screen.
  2. Click [Register] button.

Add keywords

To add keywords you want to boost:

Note
  • Up to 1,000 words can be added; Korean only is supported.
  • It is recommended to register 500 words or fewer. Registering more than 500 words may degrade performance.

You can add keywords using either method below:

Upload keyword file

To upload an Excel file and add multiple keywords at once:

  1. Prepare an Excel file containing the keywords.
    • In step 4, click Upload template to view the keyword file template.
  2. In the domain's Builder, click the Keyword Boosting menu.
  3. Click [Upload] button.
  4. When the upload popup appears, drag a file into the window or click the Click here. Drag the keyword file from your local PC into the area, drag and drop the file with your mouse, or click here. Click the area to select the keyword file.
  5. Click [OK] button.
    • Overwrite: Enable the checkbox to delete all existing keywords and register only the new keywords.
Note

If the file contains keywords that duplicate existing messages, the upload will fail. Remove duplicate keywords or enable overwrite when uploading.

Add Keywords Individually

To add keywords directly in the Builder:

  1. In the domain's Builder, click the Keyword Boosting menu.
  2. Enter the keyword you want to add. Click the input area and type the keyword.
  3. Click [Add] button.

Edit Keywords

To edit a registered keyword:

  1. In the domain's Builder, click the Keyword Boosting menu.
  2. In the keyword list, click the edit icon i-clovaspeech-edit for the keyword you want to modify.
  3. Click the keyword input field, edit the keyword, and then click i-clovaspeech-keywordeditcheck to save.
    • To cancel editing, click i-clovaspeech-keywordeditcancel.

Download Keywords

To download registered keywords in bulk:

  1. In the domain's Builder, click the Keyword Boosting menu.
  2. In the keyword list, select the checkboxes for the keywords you want to download.
    • Multiple keywords can be selected at once.
  3. Click [Download] button.
    • An Excel file containing the keywords and weight information will be downloaded.

Delete Keywords

To delete registered keywords:

  1. In the domain's Builder, click the Keyword Boosting menu.
  2. In the keyword list, select the checkboxes for the keywords you want to delete.
    • Multiple keywords can be selected at once.
    • You can also delete an individual keyword immediately by clicking [Delete] button.
  3. Click [Delete Keywords] button.
  4. When the confirmation popup appears, click [OK] button.

Correction of Recognition Results

Recognition result correction allows you to adjust or transform recognized text through post-processing. In the Recognition Correction menu, you can register and manage correction messages.

Recognition Correction Interface

A basic overview of the Recognition Correction menu interface for using the builder is as follows.

clovaspeech-builder_keyword_ko

Component Description
① Menu name Shows the current menu name.
② Register messages Deploy messages to the message server.
③ Message management Upload message files, download registered messages, delete messages.
④ Search box Search messages.
⑤ Message list List of messages currently displayed.

Register Messages

To register added messages on the server:

  1. Add the messages.
    • Register messages using the message input interface.
  2. Click the Register button.
Note
  • Up to 50,000 rows can be added; Korean only is supported.
  • It is recommended to register 40 words or fewer per message.

Add Messages

To add messages that you want to correct:

Use one of the following methods:

Upload Message File

To upload an Excel file and register multiple messages at once:

  1. Prepare an Excel file that includes the messages.
    • In step 4, click Upload Template to view the template.
  2. In the domain's Builder, click the Recognition Correction menu.
  3. Click [Upload] button.
  4. When the upload popup appears, drag a file into the window or click the Click here. Drag the keyword file from your local PC into the area, drag and drop the file with your mouse, or click here. Click the area to select the keyword file.
  5. Click [OK] button.
    • Overwrite: Enable the checkbox to delete all existing keywords and register only the new keywords.
Note

If the file contains messages that duplicate existing messages, the upload will fail. Remove duplicate messages or enable overwrite when uploading.

Add Messages Individually

To add messages directly in the Builder:

  1. In the domain's Builder, click the Recognition Correction menu.
  2. In the message input fields, enter the required values (Type, Before Correction, After Correction).
  3. Click [Add] button.

Edit Messages

To edit a registered message:

  1. In the domain's Builder, click the Recognition Correction menu.
  2. In the message list, click i-clovaspeech-edit for the message you want to modify.
  3. Click the message input fields, edit the message, and then click i-clovaspeech-keywordeditcheck.
    • If you want to cancel editing the message, click i-clovaspeech-keywordeditcancel.

Message Download

To download all registered messages at once:

  1. In the domain's Builder, click the Recognition Correction menu.
  2. In the message list, select the checkbox for the messages you want to download.
    • You can select multiple messages at the same time.
  3. Click [Download] button.
    • An Excel file containing the selected messages will be downloaded.

Message Deletion

To delete registered messages:

  1. In the domain's Builder, click the Recognition Correction menu.
  2. In the message list, select the checkbox for the messages you want to delete.
    • You can select multiple messages at the same time.
    • You can also delete a message immediately by clicking its [Delete] button.
  3. Click [Delete messages] button.

Check API Call Information and Domain Information

In the Settings menu, you can check the integration information required for API calls and the information of the domain connected to the Builder.

Check API call information

To check the integration information required for API calls:

Note

You can call the API to send audio files for recognition and receive recognition results. For more information about calling the API, see CLOVA Speech API Guide.

  1. In the domain's Builder, click the Settings menu.
  2. Click the [Integration information] tab.
  3. Check the domain's Secret Key and CLOVA Speech Invoke URL.
    • [Create] button: Click to create or regenerate the Secret Key.
    • [Copy] button: Click to copy the information to the clipboard.

Check Domain Information

To check the information of the domain connected to the Builder:

  1. In the domain's Builder, click the Settings menu.
  2. Click the [Domain information] tab.
  3. Check the domain information connected to the Builder.
    • Domain information
      • Domain name: Name of the domain
      • Domain code: Code of the domain
      • Type: Service plan applied to the domain
    • Storage settings
      • Result file storage path: Object Storage path for saving recognition result files
      • Input file storage path: Object Storage path for selecting input files
      • [Go to Object Storage] button: Click to move to the Object Storage console interface