UEL Baby Dev Lab

Speech coding – third pass speech identification, affect and intensity

Speech coding – third pass speech identification, affect and intensity

Mum vocalisations

  1. Coding is done on this webpage: https://uelbabydev.com/onacsa-home-audio-coding-phase-three-v1/
  2. Voiced segments from hour-long audiochunks of home audio data are coded one-by-one.
  3. Prior to coding the VAD (automated Voice Activity Detector) identifies the voiced audio – and from this the onset (start) and offset (end) times for each vocalisation are calculated.
  4. Each audiochunk has already been coded to identify WHO is speaking – this coding will be to decide the type of vocalisation, as well as the affect and intensity as well as any errors identified in the first and second stages. 
  5. There are approximately XXX speaker identified vocal segments ‘vocalisations’ for each hour.
  6. The script plays the audio segment for each identified vocalisation and gives a series of options for each segment.