RE: Virtual Assistants Discussions at SpeechTEK

The W3C has set up a Github repository for us where we can upload white papers and other drafts at http://github.com/w3c/voiceinteraction. I put together a template document that we can use, based on the W3C’s sample for Community Group documents (https://www.w3.org/community/src/css/spec/sample). The template is in a folder in the Github repo under “voice interaction drafts”. 

Now we need volunteers for white paper editors – please send a note to the list on the topic(s) you’d like to work on, and when you’d be able to get a draft ready for group discussion. We can work individually or in teams.

Remember that these papers can start out very simply as introductory use cases, requirements, or issue papers, or as ideas mature, we can even publish specifications (not formal W3C standards, but specifications that could be transitioned to a Working Group for standardization). This is a great opportunity to publish ideas and get feedback. 

 

From: Deborah Dahl [mailto:dahl@conversational-technologies.com] 
Sent: Wednesday, April 26, 2017 7:07 AM
To: 'Dirk Schnelle-Walka' <dirk.schnelle@jvoicexml.org>
Cc: public-voiceinteraction@w3.org
Subject: RE: Virtual Assistants Discussions at SpeechTEK

 

Thanks, Dirk. 

I think mid-June would be a good timeframe for initial white paper drafts, and I like your suggestion to use a common storage area. GitHub is another option, and I think we could get a repo set up in the W3C area (https://github.com/w3c), if we could get some help from Kazuyuki, and assuming that it could be set up so that everyone could write to it. Kazuyuki, would you be able to set up a repo on GitHub for us?

Now we need to sign up to write draft white papers. Ideally, they should include sections on use cases, requirements, a gap analysis (what existing standards or proposals are relevant, and (optionally) any ideas about what a proposal to address the issue would look like. I can prepare a template.

Best,

Debbie

 

From: Dirk Schnelle-Walka [mailto:dirk.schnelle@jvoicexml.org] 
Sent: Wednesday, April 26, 2017 4:57 AM
To: Deborah Dahl <dahl@conversational-technologies.com <mailto:dahl@conversational-technologies.com> >
Cc: public-voiceinteraction@w3.org <mailto:public-voiceinteraction@w3.org> 
Subject: Re: Virtual Assistants Discussions at SpeechTEK

 

Sounds interesting. Do you have a timeline for the white papers in mind?

 

Email is IMHO not a good option to circulate documents. Does it make sense to create a common storage on Dropbox, Google drive or similar to collect them?

 

Dirk

 

 

Am 25.04.2017 22:32 schrieb Deborah Dahl <dahl@conversational-technologies.com <mailto:dahl@conversational-technologies.com> >:

Hello,

We had two discussions at SpeechTEK today on standards for virtual assistants -- an informal morning discussion and a Birds of a Feather lunch. The goal was to get feedback on our current ideas for possible standards and get some new ideas from the SpeechTEK community. I think we had good participation, about 20 people altogether, including several current participants.

We reviewed some of our current ideas, for example: 

1. A mechanism for registration of virtual assistants, along with metadata describing the assistant. This metadata could include, for example, capabilities of the assistant, a phone number, and an associated website. This would support discovery of virtual assistants, either by other virtual assistants, or by users.

2. Protocols for communication between virtual assistants

3. semantics for common concepts (like time)

4. a format for ngram language models

5. a dialog markup language that could be used for declarative descriptions of dialogs. 

 

The first idea seemed to be of the most interest.

 

New ideas:

1. standard support for lower-level turn taking, separating prompting from recognition

2. support for common ways of describing users

3. change name and scope of group to include text-based interaction

4. prepare a document on best practices for virtual agent interaction design (this could be a joint effort with AVIxD (Association of Voice User Interface Designers)

5. a dialog annotation format for training statistical dialog models

6. support for omnichannel interaction (for example, a format for an enterprise-wide common dictionary)

7. keeping track of people as they move through a customer journey

8. reusable SCXML-based dialog components

 

Next steps would include group participants preparing white papers on topics of interest (they could be these topics or other topics that aren't listed here), circulating them to the group for comment, and publishing them as W3C Notes.

 

Debbie