1

I have a dialog agent created through DialogFlow. I want to have a conversation with this agent on a Google Home device.

The problem:

The dialogflow API (ex. dialogflow-nodejs-client-v2) gives full access to agents built in DialogFlow. Most importantly, users can interact with the system either through text input or speech input (as a .wav file or an audio stream). When you send a request to the DialogFlow agent (ex. detect intent from audio), it returns this happy response object, which crucially includes a "speechRecognitionConfidence".

But! When interacting with the dialogue agent through a GoogleAssistant App, the request object sent to a webhook is missing the "speechRecognitionConfidence" value. This means that:

  1. I don't have the input audio
  2. I don't have the ASR confidence

Questions:

  • Is it possible to send the ASR confidence (and any other useful info) to a webhook?
  • Is there another way to access the ASR confidence (ie by making an API call)?
  • Is there a way to run a program built using the dialogflow API on a Google Home (or through the google assistant)?

Thank you in advance for any help. I've been struggling through endless documentation without success.

lakhesis
  • 111
  • 1
  • 1
  • 7
  • Perhaps the Actions SDK would be helpful here? But how would this circumvent the issues stated above? – lakhesis Apr 12 '18 at 19:39
  • What I know is that if you use a Google Assistant App, then your app only have access to the transcription of the speech, which will trigger intents. I assume that the Speech to text is done in the device (ie Smart Speaker) and therefore is invisible in the app and no confidence score is given. You can simulate your app in the web simulator in the Actions on google console [over here](https://console.actions.google.com/). Just create a project, select build with dialogflow, import your project and you will be able to simulate it – Rémi C. Apr 13 '18 at 14:15

0 Answers0