15:00:21 RRSAgent has joined #voiceinteraction 15:00:21 logging to https://www.w3.org/2021/10/27-voiceinteraction-irc 15:02:16 meeting: voice interaction 15:02:23 scribe: ddahl 15:02:37 chair: Debbie 15:03:28 present:dirk,debbie,bev,paul grenier 15:03:37 PaulG_ has joined #voiceinteraction 15:03:40 https://www.w3.org/TR/spoken-html/ 15:04:19 present+:kazuyuki 15:04:57 https://lists.w3.org/Archives/Public/public-voiceinteraction/2021Oct/0012.html 15:05:10 kaz has joined #voiceinteraction 15:05:42 debbie: review discussion from last week's breakout groups 15:06:04 https://web-eur.cvent.com/event/2b77fe3d-2536-467d-b71b-969b2e6419b5/websitePage:efc4b117-4ea4-4be5-97b4-c521ce3a06db 15:07:07 https://www.w3.org/2021/10/20-voice-minutes.html 15:07:10 https://www.w3.org/2021/10/19-voice-minutes.html 15:08:51 debbie: possibility of a voice workshop 15:09:29 present+ mustaq ahmed 15:09:52 kaz: how to integrate speech API and SSML in a workshop 15:10:21 ...organized session with voice interoperability session 15:10:54 kaz: decided to have a workshop, not voice but smart agent workshop 15:11:19 ...interoperability, voice interface, accessibility 15:11:47 ...some overlap with semantic web? is that too broad? 15:12:01 ...when we talk about smart agents 15:12:06 Zakim has joined #voiceinteraction 15:12:31 ...one or two days, online 15:13:04 kaz: online workshop is much easier 15:13:15 rrsagent, make log public 15:13:19 rrsagent, draft minutes 15:13:19 I have made the request to generate https://www.w3.org/2021/10/27-voiceinteraction-minutes.html kaz 15:13:29 Perhaps hybrid online and in person? 15:13:53 ...usually takes six months or so, around May 15:14:35 Include the Cognitive Inclusion COGA group 15:15:01 bev: could also do a hybrid event 15:15:22 q? 15:15:23 ...cognitive inclusion group has some overlap 15:15:28 q+ 15:15:48 Information Architecture Community Group is also supportive and can participate 15:15:56 kaz: should have a dedicated session on accessibility 15:17:03 debbie: to attend need to prepare a position paper and the program committee will review 15:17:04 anyone interested can prepare submission position proposal to program committee 15:17:08 -> https://www.w3.org/2021/06/smartcities-workshop/index.html e.g., Smart Cities Workshop CfP 15:17:46 ...prerecorded videos with captions 15:18:09 ...need to be provided 15:18:48 s/...pre/debbie: pre/ 15:19:09 debbie: other topics like Open Voice Network 15:19:19 ...could be included 15:20:19 paul: disambiguation in Spoken HTML spec, machine learning has its own heuristics, but in the meantime author-controlled pronunciation would be useful 15:20:37 q? 15:20:38 ack k 15:21:39 paul: trying to get feedback from implementers, can't just bring SSML into HTML 15:22:01 ...will have some representation of SSML into HTML, expecially pronunciation 15:22:51 ...could use this in machine learning 15:22:54 s/expe/espe/ 15:25:27 paul: word clusters could be modified by IPA 15:25:57 ...a layer could map pronunciation to IPA 15:26:25 ...and match to user's intent 15:26:50 q+ 15:27:17 ...language, cultural information is missing 15:29:31 ...when input happens, e.g. speech difficulty is like a transform over standard language 15:29:49 ...we can transform from word or from sound 15:30:30 ...they could have had a stroke or something that altered their speech 15:30:55 bev: iPads for elderly after dental surgery 15:31:06 ...speech was different 15:31:30 ...could we use this to transform speech 15:32:07 paul: for SpeechHTML this is the first step 15:32:42 ...if the system doesn't find a match it could look for transforms 15:33:21 ...could be useful in a kiosk situation where user can't add their preferences 15:34:53 kaz: two points, one for speech synthesis and one for speech recognition 15:35:21 ...for speech output it would be nice to have another layer to get correct pronunciation 15:35:42 Kaz: acoustic model 15:36:00 kaz: for speech input, we might want to include another mechanism 15:36:04 Kaz: command input expected actions, speech and gesture 15:36:16 ...such as hardware switch, gesture 15:36:34 ack k 15:37:29 debbie: also Natural Language Interfaces spec 15:37:52 q+ 15:38:34 ack k 15:38:43 debbie: can join the program committee 15:38:54 paul: maybe could join 15:39:23 bev: could join program committee 15:39:29 ...depends on timing 15:39:32 i/can/kaz: btw, it would be really nice if you all by chance could join the Program Committee for the expected workshop :)/ 15:42:34 architecture document https://w3c.github.io/voiceinteraction/voice%20interaction%20drafts/paArchitecture-1-2.htm 15:43:10 i/arch/topic: Architecture document/ 15:43:21 IPA means "intelligent personal assistant" 15:44:10 i/spoken-html/topic: Breakout feedback and expected workshop/ 15:44:22 rrsagent, draft minutes 15:44:22 I have made the request to generate https://www.w3.org/2021/10/27-voiceinteraction-minutes.html kaz 15:44:33 dirk: (reviews input architecture) 15:46:13 ...provider selection strategies can be used to select providers 15:48:31 dirk: (goes through output path) 15:52:21 bev: question about intent sets 15:52:41 ...could you talk about that a little more 15:53:00 dirk: information that could be used to fill in slots 15:53:17 bev: is that a standard? 15:53:35 dirk: for now this is pretty abstract 15:54:02 bev: would that include security information 15:54:19 dirk: thinking in terms of SISR, more like that 15:54:59 ...have to distinguish between local intent sets and provider intent sets 15:55:27 debbie: Emotion ML 15:55:54 PaulG_ has left #voiceinteraction 15:58:02 debbie: could be used in input and output 15:58:47 kaz: don't have any specific comments, should discuss with browser and speech vendors 15:59:00 ...should present at workshop 15:59:25 ...EMMA would be a good format for all this data 15:59:45 kaz: would like to integrate MMI architecture and SCXML 16:01:13 ...DID (decentralized identifier) standard, there are many implementers, based on blockchain, should be a Recommendation soon 16:01:44 ...that can be used to identify users and devices, also discovery can be handled this way 16:02:27 debbie: next call will be November 10 16:02:32 s/SCXML/SCXML for interaction management with WoT standards for device management/ 16:03:51 rrsagent, format minutes 16:03:51 I have made the request to generate https://www.w3.org/2021/10/27-voiceinteraction-minutes.html ddahl 16:04:00 rrsagen, make logs public 18:27:47 ddahl has left #voiceinteraction 18:58:31 Zakim has left #voiceinteraction