| Table of Contents |
|---|
Purpose
This document outlines the Speech EG’s commitment proposal to CES Demo 2019. It also highlights the dependencies on Audio High Level, Application Framework and Native App Integration teams in order to deliver a successful demo that demonstrates our vision of multi agent architecture.
...
Wake word detection will not be supported. As of today, AGL Audio 4a, doesn’t yet support storing a persistent audio input buffer can be shared between multiple consumers. In this case wake word module and high-level voice services. We discussed in detail about the audio design to support wake word use cases. However there is no further information on the timeline for having this support to be baked into AGL Audio framework.
Major Tasks
| # | Component | Ownership |
| 1 | Voice Service High Level (VSHL) Development | Amazon to deliver first draft the can be open sourced and submitted to AGL repository. |
| 2 | Alexa Voice Agent Development | Amazon |
| 3 | QT based App for Template Rendering | Amazon |
| 4 | Native App Development and Integration With Voice Service High Level | Linux Foundation / IOT.BZH |
| 5 | Audio Input Output Support | Linux Foundation / IOT.BZH |
| 6 | Application Framework Support | Linux Foundation / IOT.BZH |
External Dependencies
Applications should be able to launch themselves when they receive intents from Voice Service Interaction Manager.
Audio High level needs to create 4 audio roles for Alexa to do audio output.
Audio High Level needs to create 1 audio role for High Level Voice Service to do audio input.
Speech Chrome Application needs to be implemented to display different dialog states (IDLE, LISTENING, THINKING, SPEAKING) of the voice agent.
Template Runtime Application to show the templates that are delivered as responses by each voice agents. If we can't standardize the language for this template, then as a workaround, Amazon will implement Alexa UI Template Runtime Application that can render Alexa templates for CES Demo 2019.
...
User starts speaking and says, “Alexa, Set an Alert for next 1 minute” or “Set an Alert for next 1 minute.”
Alexa Voice Agent will prompt TTS that Alert is set.
Alexa Voice Agent will call Voice Interaction Manager’s Alerts::Publish API to publish new Alert state.
Alexa Voice Agent will play Alerts Audio after one min.
...
Phone Call Control
User starts speaking and says "Alexa, Call Bob"
Alexa Voice Agent will prompt TTS to disambiguate the contact request.
Alexa Voice Agent will call Voice Interaction Manager's Call:: Publish API to publish a DIAL event.
Dialer app on the AGL reference platform will pick the event and initiate call based on the event payload.
Dialer app will call Voice Interaction Manager's Call:: Publish API to publish a CALL_ACTIVATED downstream event for Alexa Voice Agent to update it's context.
CES Demo Integration Meetings
To join : https://appear.in/agl@iotbzh
Next Meeting : 8:00 AM PST on November 30th, 2018
IRC : #automotive
Minutes of Meeting
November 28th, 2018
Alexa Voice Agent is tested and working with Microchip array and Fiberdyne at AGL F2F workshop in Germany. Thanks to Shotaro and IOT.bzh. The main purpose of the integration session is well under control.
Action Items:
- IOT.bzh to provide the image and SDK that will be used for CES demo today.
- IOT.bzh to help with running HTDocs on dev machine that connects to VSHL on a Renesas board
- IOT.bzh to work with Naveen & Shotaro to integrate the phone control capability with Dialler app.
- IOT.bzh to look into the VSHL config file to fix the problem with two VSHL icons visible on the homescreen, one for the html app and one for the service.
- Shotaro to host the low-level Alexa voiceagent widget privately and share it with IOT.bzh for testing and integration.
- Naveen to provide a temporary work around for refreshing the auth tokens required for low-level voice agent.
- Naveen to provide an update on our discussions with ICS. The company that we are trying to engage for building Alexa UI and Login Apps.
November 30th, 2018
- IOT.bzh provided the AGL images that will be used for CES.
- IOT.bzh is temporarily unblocked on Alexa Voice Agent authentication. Naveen updated that this is only a temporary solution and we will have a proper CBL auth solution in place before the December 10th SF F2F session.
- Naveen updated IOT.bzh that Alexa apps will be implemented by ICS.
Action Items:
- IOT.bzh to look into the VSHL config file to fix the problem with two VSHL icons visible on the homescreen, one for the html app and one for the service.
- IOT.bzh to integrate Dialer app with phonecontrol messages from VSHL and also integrate the app launching plugin with VSHL.