Internet Industry Search Engine

Building a Voice Assistant for Enterprise

Source: infoq.com

Jan 22, 2019 9:13 PM 1+ mon ago

Manju Vijayakumar talks about Einstein Assistant - an AI Voice assistant for enterprises that enables users to "Talk to Salesforce". She goes through the high-level architecture and workflow starting from Automatic Speech Recognition (ASR) on device to using NLP for identifying entities and intents in a single dialog conversation text.Read more.

Search Builder

(Click to add to search box)
Search Suggestions Level 1
voice assistant  Acme Corporation  Chris Hopkins  Automatic Speech Recognition  language understanding  AI Voice assistant  entity recognition  speech recognition  dialog conversation text  data sets  meeting notes  Voice Assistant  Natural Language Decathlon  language understanding services  language understanding capabilities  savings account number  sentiment analysis model  language understanding models  speech recognition models  custom schemas  Conversational AI Ecosystem  JP Morgan  Salesforce CRM system  relationship graph  Linux kernel API  sentiment analysis  legacy data systems  Salesforce AI research  custom data sets  customer sales meetings  customer relationship management  language processing tasks  bottom layer  sequence model  date entity  person entity  language processing  predefined category  Manju Vijayakumar  use voice  meeting note  voice recognition  opening scene  check error  Japanese entities  custom dataset  intent model  NLP issue  chatbots world  Japanese company  ASR models  Misspelled pronouns  action item  NLP world  language API  NLP algorithms  failback mechanism  entity resolution  context management  record ID  prediction work  future Considerations  prediction request  optimized models  language APIs  future considerations  Action item  NLP tasks  network architectures  
Search Suggestions Level 2
voice assistant  cars Amazon Alexa  Alexa Tries Hard  Voice Assistant  Soundbar Presentation  Microservice Approach  
Search Suggestions Level 3
Command Bar  Polk Command Bar  Fire TV Cube  Oracle Digital Assistant  voice assistant  team communication apps  Fire TV sticks  conference Pivotal Training  Many soundbar setups  BMW Assistant support  voice search works  Polk Connect app  trouble understanding dialogue  Command Bar volume  Fire TV  TiredSound isn t  use Fire TV  newscaster voice  Amazon Echo speaker  High Velocity Sales  voice commands  home theater experience  press release contextualizing  Image Credit  customer experiences  voice technology  voice assistants  Microservice Approach  Spotify app  Alexa speaker  Alexa setup  Chromecast support  Wireless subwoofer  WiredGood sound  Whisper mode  bedtime stories  Kahlil Gibran  Amazon account  Marcus Lemonis  Capgemini forecasting  Wikipedia entries  business empire  question Alexa  reality TV  way newscasters  Neural TTS  Alexa Skills  Echo features  affiliate commission  TV codes  re feeling  HDMI cables  dialogue quality  word Voice  tech giant  sound quality  response time  Alexa soundbar  Alexa team  sales managers  engineers smushed  Michael Bay  Amazon Echo  Panasonic TV  Alexa support  Alexa device  Amazon page  Alexa Polk  TV product  Sorta Smart  InfoQ account  InfoQ experience  Echo devices  Related Topics  Polk team  Oracle customers  language understanding  soundbar money  Pivotal technologies  Service Cloud  TV speaker  Dreamforce conference  Alexa features  San Francisco  chat apps  blong sound  climate control  tire pressure  oil level  engine settings  language requests  Salesforce records  Azure cloud  BMW assistant  

**Content contained on this site is provided on an “as is” basis. 4Internet, LLC makes no commitments regarding the content and does not review it, so don't assume that it's been reviewed. What you see here may not be accurate and should not be relied upon. The content does not necessarily represent the views and opinions of 4Internet, LLC. You use this service and everything you see here at your own risk. Content displayed may be subject to copyright. Content is removed on a case by case basis. To request that content be removed, contact us using the following form: Contact Us.