Top Banner
Nick Landry Senior Technical Evangelist – Microsoft [email protected] Blog: AgeofMobility.com @ActiveNick | github.com/ActiveNick Microsoft Cognitive Services: Building Smart Applications with Speech, NLP & Vision
37

Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Jan 07, 2017

Download

Technology

Nick Landry
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Nick LandrySenior Technical Evangelist – Microsoft

[email protected]

Blog: AgeofMobility.com

@ActiveNick | github.com/ActiveNick

Microsoft Cognitive Services:

Building Smart Applications

with Speech, NLP & Vision

Page 2: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 3: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Microsoft Cognitive ServicesGive your apps a human side

Page 4: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Microsoft Cognitive ServicesGive your apps a human side

Cognitive Services API Collection

Page 5: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 6: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Bringing it all together The Seeing AI App

Computer Vision, Image, Speech Recognition, NLP,

and ML from Microsoft Cognitive Services

Watch Video HereRead Blog Here

Page 7: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

EmotionSpeaker

Recognition

Speech

Custom

RecognitionComputer Vision

Face

Video

microsoft.com/cognitive

Linguistic Analysis

Language

Understanding

Bing Spell Check

Entity Linking

Knowledge

Exploration

Academic

Knowledge

Bing

Image Search

Bing

Video Search

Bing

Web Search

WebLM

Text Analytics Recommendations

Bing

Autosuggest

Bing

News SearchTranslator

Page 8: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

EmotionSpeaker

Recognition

Speech

Custom

RecognitionComputer Vision

Face

Video

microsoft.com/cognitive

Linguistic Analysis

Language

Understanding

Bing Spell Check

Entity Linking

Knowledge

Exploration

Academic

Knowledge

Bing

Image Search

Bing

Video Search

Bing

Web Search

WebLM

Text Analytics Recommendations

Bing

Autosuggest

Bing

News SearchTranslator

Page 9: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 10: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Computer Vision API

Distill actionable information from

images

Video API

Analyze, edit, and process videos within

your app

Face API

Detect, identify, analyze, organize, and

tag faces in photos

Emotion API

Personalize experiences with

emotion recognition

Vision

Page 11: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 12: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Updated Computer Vision API

Content of Image:

Categories v0: [{ “name”: “animal”, “score”: 0.9765625 }]

V1: [{ "name": "grass", "confidence": 0.9999992847442627 },

{ "name": "outdoor", "confidence": 0.9999072551727295 },

{ "name": "cow", "confidence": 0.99954754114151 },

{ "name": "field", "confidence": 0.9976195693016052 },

{ "name": "brown", "confidence": 0.988935649394989 },

{ "name": "animal", "confidence": 0.97904372215271 },

{ "name": "standing", "confidence": 0.9632768630981445 },

{ "name": "mammal", "confidence": 0.9366017580032349, "hint": "animal" },

{ "name": "wire", "confidence": 0.8946959376335144 },

{ "name": "green", "confidence": 0.8844101428985596 },

{ "name": "pasture", "confidence": 0.8332059383392334 },

{ "name": "bovine", "confidence": 0.5618471503257751, "hint": "animal" },

{ "name": "grassy", "confidence": 0.48627158999443054 },

{ "name": "lush", "confidence": 0.1874018907546997 },

{ "name": "staring", "confidence": 0.165890634059906 }]

Describe0.975 "a brown cow standing on top of a lush green field“

0.974 “a cow standing on top of a lush green field”

0.965 “a large brown cow standing on top of a lush green field”

Page 13: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Start coding

microsoft.com/cognitive

Page 14: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 15: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Speech

Bing Spell Check API

Detect and correct spelling mistakes within your app

Language Understanding Intelligent Service

Teach your apps to understand

commands from your users

Web Language Model API

Leverage the power of language models trained on web-scale

data

Linguistic Analysis API

Easily parse complex text with language

analysis

Text Analytics API

Detect sentiment, key phrases, topics, and language from

your text

Language

Page 16: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Reduce labeling effort with interactive featuring

Seamless integration to Speech API

Deploy using just a few examples with active learning

Supports 5 languages (English, Chinese, Italian, French, Spanish)

Language Understanding Models

Page 17: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

{“entities”: [

{“entity”: “flight_delays”,“type”: “Topic”

}],“intents”: [

{“intent”: “FindNews”,“score”: 0.99853384

},{

“intent”: “None”,“score”: 0.07289317

},{

“intent”: “ReadNews”,“score”: 0.0167122427

},{

“intent”: “ShareNews”,“score”: 1.0919299E-06

}]

}

“News about flight delays”

Language Understanding Models

Page 18: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Your conversation logic

Logic

Web Service

Your Bot

LUIS

Page 19: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Start coding

microsoft.com/cognitive

Page 20: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 21: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://www.microsoft.com/cognitive-services/en-us/text-analytics-api

Page 22: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Start coding

microsoft.com/cognitive

Page 23: Cognitive Services: Building Smart Apps with Speech, NLP & Vision
Page 24: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://www.microsoft.com/en-us/translator/products.aspx

Page 25: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Start coding

microsoft.com/cognitive

Page 26: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Easy

F lex ib le

Qual i ty

Why Microsoft Cognitive Services?

Page 27: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Developer Resources

Preview Pricinghttps://www.microsoft.com/cognitive-services/en-us/pricing

Documentationhttps://www.microsoft.com/cognitive-services/en-us/computer-vision-api/documentation

Client SDKshttps://github.com/Microsoft/ProjectOxford-ClientSDK

https://github.com/felixrieseberg/project-oxford (nodejs)

https://github.com/southwood/project-oxford-python

Example Codehttps://github.com/jsturtevant/happy-image-tester-django

https://github.com/jsturtevant/happy-image-tester-nodejs

Join Our Communityhttps://stackoverflow.com/questions/tagged/microsoft-cognitive

https://social.msdn.microsoft.com/forums/azure/en-US/home?forum=mlapi

https://cognitive.uservoice.com/

Page 28: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://blog.xamarin.com/performing-ocr-for-ios-android-and-windows-with-microsoft-cognitive-services/

https://github.com/pierceboggan/smarter-apps/tree/master/ExpenseIt/

https://blog.xamarin.com/adding-facial-recognition-to-your-mobile-apps/

https://github.com/pierceboggan/smarter-apps/tree/master/talk/employee-directory/

https://github.com/xamarin/mini-hacks/tree/master/microsoft-cognitive-services/solutions

Page 29: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://github.com/DotNetToscana/See4Me

https://github.com/ActiveNick/BingTranslateDemo

https://github.com/ActiveNick/CognitiveServices-Demo-Face

https://github.com/ActiveNick/CognitiveServices-Demo-EntityLinking

https://github.com/ActiveNick/CognitiveServices-Demo-TextAnalytics

Page 30: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://channel9.msdn.com/Events/Build/2016/B878

https://channel9.msdn.com/Events/Build/2016/B855

Page 31: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

https://channel9.msdn.com/Events/Build/2016/T620

https://channel9.msdn.com/Events/Build/2016/B834

https://channel9.msdn.com/Events/Build/2016/B833

Page 32: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

http://developer.microsoft.com/cortana

http://AgeofMobility.com/Cortana

Page 33: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Online Microsoft training delivered by experts to help technologists continually learn

Hundreds of courses for developers, IT Pros, students, entrepreneurs and enthusiasts

11 different languages

3M+ students registered

Build your own Learning Plan

All free!

http://mva.microsoft.com

Page 34: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

• Universal Windows App Developmentwith Cortana and the Speech SDK

• Available for on-demand viewing now:http://aka.ms/CortanaMVA

Page 35: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

• Channel 9 Show

• Visual Studio Toolboxwith Robert Green• New Voice Commands

• Integration with Cortana’s canvas

• Background Voice Commands

• Continuous dictation

• Poutine in Montreal!

https://channel9.msdn.com/Shows/Visual-Studio-Toolbox/App-Development-with-Cortana

More Cortana Dev on Windows 10

Page 36: Cognitive Services: Building Smart Apps with Speech, NLP & Vision

Thank You!Slides are in SlideShare. Demos are on GitHub.Contact me and let me know what you build, I will be happy to help promote your apps.

Blog: AgeofMobility.com

Twitter: @ActiveNick

Email: [email protected]

Apps: www.bigbaldapps.com

LinkedIn: linkedin.com/in/activenick

GitHub: github.com/ActiveNick

Slideshare: slideshare.net/ActiveNick

Page 37: Cognitive Services: Building Smart Apps with Speech, NLP & Vision