Conversational ULS: Talking to Siri, Alexa, and Your Web Browser
summary
Demos show concrete tech: the Web Speech API (speech synthesis + recognition), SSML for richer TTS, and browser support notes (Edge implements SSML; many browsers rely on Google cloud recognition). Claims include Gartner’s 30% of interactions by voice, Roku and Echo examples, and the wake‑word pattern where local detection then ships audio to the cloud. Expect practical code (MDN examples, JS speech grammar) and an accessibility win: an assistive voice readout used by a child to speak her own school report.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 2:27Voice assistants at home
- 4:18Conversational IoT trend
- 6:52Natural vs command UIs
- 9:01Open standards for conversational UIs
- 10:51Voice synthesis in pop culture
- 14:16W3C Web Speech API
- 16:41Speech synthesis basics
- 19:55SSML for voice output
- 22:45Speech recognition challenges
- 25:47Pure voice UIs rise
- 27:12Siri’s origins
- 30:41Live speech recognition demo
- 34:41Bounded grammar & JSGF
- 37:13Alexa skills with web tech
- 38:18Fundamentals vs frameworks
- 38:59Accessibility impact
- 40:29Q&A
related talks
38mConversational UIs: Talking to Siri, Alexa, and Your Web Browser
58mAdding Speech to your Web App_UIArchitecture
51mYou talkin' to me?
49mDesigning voice interfaces
32mConversational Semantics for the Web
29mFinding Your Voice: Building Screenless Interfaces with Node.js
45mNavigation with a Voice Assistant
28mLet's Get Chatty with Conversational Interface in JavaScript