Logo long text klein

    • Welcome to this website
    • What drives us
    • Who we are
    • Supporting Partners
    • Contact
    • Member login
    • About
  • Research domains
    • Oral History
    • Computational Linguistics
    • Sociolinguistics
    • Language and Speech Technology
  • Tech & Tools
    • Technologies and tools for speech data
    • Automatic Speech Recognition
    • Forced Alignment
    • Transcription
    • Emo-Spectre
    • Qualitative Data Analysis
    • Computational Linguistics
    • Subtitles
    • Software developed by our team
  • Workshops
    • EHRI 2022
    • ICMI 2020
    • CLARIAH OH Workshop 2019
    • CLARIN Workshop Sofia 2019
    • DH2019 Workshop
    • München Workshop 2018
    • Arezzo Workshop 2017
    • Utrecht Workshop 2016
    • Oxford Workshop 2016
  • Publications
  • Transcription Portal
  • Guidelines
    • Converting Audio
    • About Transcription
    • Metadata Schemas
    • New Digital Recordings
  • News
  • Data

manuals2

  • Converting Audio
  • About Transcription
  • Metadata Schemas
  • New Digital Recordings

New Digital Recordings

For new AV-recordings it makes sense to create a recording situation, optimized for technology such as ASR, Aligment, Emotion Detection, Facial Expression Analyses and more.

microfoonA good example is the VXi VoxStar UC Bluetooth HeadsetSome small guidelines:

  • if possible, record each speaker on a separate audio channel via a separate microphone
  • record the speech with a high sample frequency and a 4-bit sample value (not 16-16-mono but 96-32-channel-per-speaker)
  • use microphones that have a more-or-less fixed distance to the mouth
  • use microphones that mute as much as possible the sound from other sources than the mouth of the speaker

The benefits of the approach mentioned here are great. Separate channels per speaker makes it possible to do automatic turn-taking, it prevents that a louder speaking person "overrules" a softer speaking person and the speech can be transcribed even if people are talking together.