User Tools

Site Tools


eg-speech

This is an old revision of the document!


Speech Expert Group

Goals for Expert Group

  • Create a standardized set of speech recognition APIs that app developers can use regardless of underlying speech engine
  • Natural language or grammar tree based
  • On board or cloud based speech
  • Text to Speech API
  • Signal processing for noise reduction and echo cancellation (future roadmap)
  • Grammar development tools
  • Amazon has an open API that could be used as a starting point
  • Goal is to have a straw man by the AMM in Tokyo, Feb. 20-21 with work completed by ALS in June.
  • Next step is to set up a call with the engineers from all three companies who will be working on this.

Meetings

Feb 14, 2018

Attendees:
LF: Walt, Dan
Voicebox: Andrew
Nuance: Christian, Mike
Amazon: John

Notes:

  • Amazon still internally discussing making their API available for AGL.
  • Amazon SDKs that are available publicly require an agreement with Amazon to access
    • Alexa Voice Service Device SDK
    • Alexa Skills Kit
  • Nuance interface still discussing internally. Christian made a presentation that he will send around with Nuance's ideas for the API.
  • Walt will use the minutes from these calls to lead an AMM session next week that updates the community on the EG's work.

Feb 6, 2018

Attendees:
LF: Walt, Jan-Simon
Voicebox: Andrew and Adam
Nuance: Christian, Mike
Amazon: None

Notes:

  • No word from Amazon on the availability of their API as well the link to what is publicly.
  • Nuance interface still discussing internally. Still waiting for Amazon proposal.
  • Walt will follow up with Amazon about their API. Schedule a follow up call for Tuesday, Feb 13
  • Question about how AGL handles app creation and installation

Kick off Meeting Jan 29, 2018

Attendees: Walt, Jan-Simon, Mike Chachich, John Scumniotales, Andrew Fairly, Vince Iannotti, Christian Benien (attending AMM)

Agenda for kick off meeting

  • Review expert group goals as captured above
  • Proposal for speech recognition API or TTS API from Amazon?
  • Meeting schedule (biweekly? what time?)
  • Developer commitment from EG members.
  • Reviewed agenda and notes from CES
  • John said there is ongoing internal Amazon about releasing their code. There is already an open source version or public API version. Need to find out definitively what they are talking about as the release.
    • John will send a link to what is publicly available now
    • Should wrap up internal discussions end of this week. (Feb 2)
  • Michael may have something they can release. Will discuss internally once we see what Amazon has.
  • Attending AMM: Nuance: Christen, Amazon: Shitaro and Sanjay. VBT: TBD
  • Reserve time at AMM on Thursday (1 hour)
  • Follow up Feb 6
eg-speech.1521903132.txt.gz · Last modified: 2018/03/24 14:52 by waltminer