Automatic Speech Recognition API Reference

To evaluate the Automatic Speech Recognition (ASR) accuracy of your skill, you can use the ASR APIs. If you want to use the ASR Evaluation tool in the developer console, see the Automatic Speech Recognition (ASR) Evaluation tool.

ASR implementation steps

To run an ASR evaluation, implement the APIs in the following order.

  1. Create your audio catalog:
    1. Call Create a catalog to create your new catalog.
    2. Call Associate a catalog to a skill to associate your new catalog with the skill that you're evaluating.
    3. Create the upload for your catalog by calling Catalog content upload.
    4. Upload your .zip file of audio files to the S3 URL returned by Catalog content upload. Audio files must be .mp3, .wav, .aiff, or .ogg format.
    5. After the upload completes, call Complete Upload.
    6. Call Get Upload to get the ingestion status of your upload.
  2. Create your annotation set:
    1. Call the Create annotation set API to create your empty annoation set.
    2. Call the Update annotation set annotations API to add your uploaded audio utterances to the annotation set.
  3. Run the ASR evaluation by calling the Post ASR evaluation API.
  4. Return your ASR evaluation status and results by calling the Get ASR evaluation status API and Get ASR evaluation results API.

API reference list