Audio Classification

If you want to perform audio classification tasks, such as intent or sentiment classification, you can use this template to listen to an audio file and classify the topic of the clip.

Interactive Template Preview

Labeling Configuration

<View>
  <Header value="Listen to the audio:"></Header>
  <Audio name="audio" value="$url"></Audio>
  <Header value="Select its topic:"></Header>
  <Choices name="label" toName="audio" choice="single-radio" showInline="true">
    <Choice value="Politics"></Choice>
    <Choice value="Business"></Choice>
    <Choice value="Education"></Choice>
    <Choice value="Other"></Choice>
  </Choices>
</View>

About the labeling configuration

All labeling configurations must be wrapped in View tags.

You can add a header to provide instructions to the annotator:

<Header value="Listen to the audio:"></Header>

Use the Audio object tag to specify the type and the location of the audio clip. In this case, the audio clip is stored with a url key in the data:

<Audio name="audio" value="$url"></Audio>

Use the Choices control tag to manage how the classification choices appear to annotators with showInline="true" and what selection option is used on the interface with choice="single-radio". The toName="audio" option associates the choices with the audio clip.

<Choices name="label" toName="audio" choice="single-radio" showInline="true">

You must use the Choices tag in combination with the Choice to specify the available choices to classify the audio, then close the Choices tag:

    <Choice value="Politics"></Choice>
    <Choice value="Business"></Choice>
    <Choice value="Education"></Choice>
    <Choice value="Other"></Choice>
</Choices>

Related tags

• Audio
• Choices

Related templates

• Intent Classification
• Audio Classification with Segments

Couldn't find what you were looking for? Please let us know on Slack 
If you found an error, you can file an issue on GitHub!