Closed

Emotion Recognition through Speech Analysis in Recorded Audio with Added Keyword Spotting

This project received 14 bids from talented freelancers with an average bid price of $514 USD.

Get free quotes for a project like this
Employer working
Project Budget
$250 - $750 USD
Total Bids
14
Project Description

The program simply needs to determine whether the audio input, one minute long, expresses angry or neutral emotion, and detects the following keywords: billing, disconnection, lack of knowledge, long processing, no connection, poor service. Use Support Vector Machine as classifier.

Indicate on how to train the machine in case training samples for emotion recognition or keywords will be added in the future.

The analysis of the audio input will be displayed; features, the emotion exhibited and keyword that is present.

Looking to make some money?

  • Set your budget and the timeframe
  • Outline your proposal
  • Get paid for your work

Hire Freelancers who also bid on this project

    • Forbes
    • The New York Times
    • Time
    • Wall Street Journal
    • Times Online