Keyboards? Where We’re Going, We Don’t Need Keyboards

on YouTube ↗54m

" summary

Demonstrates using Microsoft Cognitive Services — Vision API for image tagging/captioning (including celebrity recognition, coffee/party detection), LUIS for intent extraction (example: identifying “book flight” with improving scores after training on thousands of examples), and Speech-to-Text streaming to connect voice to intents. Shows a web demo wiring image upload, speech recognition, and LUIS end-to-end; it functions live but requires more training data to be reliable.

AI-written summary · about

" chapters (10)

1. 0:00Welcome
2. 3:16Sensor to AI
3. 10:07Vision API in action
4. 16:01Machine learning services
5. 26:29Speech recognition & NLP
6. 31:06AI travel app
7. 37:22Building with ML
8. 45:23Speech-to-text & TTS
9. 50:09Live speech demo
10. 52:02Future vision

" related talks

• 51mKeyboards? Where we’re going, we don’t need keyboardsDon Wibier · NDC Copenhagen 2019
• 01h 05mMicrosoft Cognitive Services: Making AI EasyJennifer Marsman · NDC London 2017
• 46mBuilding accessible experiences with AIHenk Boelman · Build Stuff 2021
• 01h 03mEasier AI allows everyone to build smart appsDavid Burela, Azadeh Khojandi · NDC London 2018
• 57mEasier AI allows everyone to build smart appsDavid Burela, Azadeh Khojandi · NDC Sydney 2018
• 53mAI for the betterDennie Declercq · NDC Sydney 2020
• 01h 00mA lap around Microsoft Cognitive Services Vision APITim Huckaby · NDC Sydney 2017
• 49mMake your applications intelligent (...)Michał Jankowski · 4Developers Kraków 2019