[Pycon] [new paper] "Aaron Bassett" - Real-time transcription and sentiment analysis of audio streams; on the phone and in the browser

[info a pycon.it]

Title: Real-time transcription and sentiment analysis of audio streams; on the phone and in the browser
Duration: 240 (includes Q&A)
Q&A Session: 0
Language: en
Type: Talk

Abstract: In this workshop, we're going to learn how to create a virtual rapporteur. A digital assistant who can join any conference call; record it and provide participants with real-time insights into the overall tone of the call. Once the call is complete, we'll look at how we can use the call recording to provide participants with a text transcript as well as meta information about the call such as the most talked about concepts, keywords and entities.

*Attendees*: This is an intermediate level workshop, you should be familiar with Python and the command line. All attendees should bring a laptop to work on, with Python 3 already installed. The [DjangoGirls installation tutorial](https://tutorial.djangogirls.org/en/installation/) is handy if you've never done this before. You will also need to sign-up for a free [Nexmo](https://nexmo.com) and [IBM Watson](https://www.ibm.com/watson) account to access their APIs.

We'll be coding the application in Python and JavaScript, with the [Hug](https://hug.rest), [Tornado](http://www.tornadoweb.org/) and [Vuejs](https://vuejs.org/) frameworks; so a knowledge of both languages would be beneficial but is not required. We will be making heavy use of several APIs, so experience with REST and WebSockets will help.

Tags: [u'audio', u'nlp', u'websockets', u'websockets', u'vertical-align: inherit;', u'>websockets </font></font>', u'><font style=', u'tornado', u'<font style=', u'AI', u'webservices']