• Back to homepage

Getting started

  • Overview

Using Vokaturi

  • Example code for C (batch)
  • Example code for C (real-time)
  • Example code for Python (batch)
  • Example code for Python (real-time)

Downloads

  • Download the SDK

Algorithms

  • Three requirements
  • Annotated databases
  • Measuring acoustic features
  • Measuring emotions

Contact us

  • Send us an email

News

  • 25 Aug 2022OpenVokaturi 4.0
  • 22 May 2020VokaturiPlus 1.6 times better
  • 20 Feb 2020OpenVokaturi 3.4
  • 2 Jun 2019OpenVokaturi 3.3
  • 8 May 2018OpenVokaturi 3.0a
View all news

News

  • 13 July, 2017

    OpenVokaturi 2.1c

    Recognize even more WAV files

  • 21 February, 2017

    Mobile World Congress 2017

  • 31 January, 2017

    OpenVokaturi 2.1b

    Recognizing more WAV files

  • 25 January, 2017

    OpenVokaturi 2.1a

    Fixes in example files

  • 16 January, 2017

    Human-level performance for VokaturiPlus

    Vokaturi has reached a milestone: the software is now just as good at recognizing emotions from the voice as human listeners are. VokaturiPlus scores 76.1% correct (cross-validated) on two emotion databases, while humans guess the speaker's intended emotion correctly in 76 percent of the cases (Sanaul Haq, Philip J.B. Jackson & James Edge 2008: "Audio-visual feature selection and reduction for emotion classification").

  • 1
  • 2
  • 3
  • 4
  • 5

Change the future with us
Send us an email for more information and partnership opportunities

Contact us now

© 2022 Vokaturi B.V. The Netherlands