Techn. Fakultät Website deprecated and outdated. Click here for the new site. FAU-Logo

PD Dr.-Ing. habil. Stefan Steidl

Alumnus of the Pattern Recognition Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg

Applying mathematically founded machine learning and pattern recognition techniques to fascinating interdisciplinary research areas: from medical image segmentation to computer-assisted diagnosis and therapy control for pathological speech to vocal emotion recognition for human-machine interaction.

FAU Aibo Emotion Corpus

Spontaneous, emotionally colored speech of children interacting with Sony's pet robot Aibo


The corpus consists of 9 hours of German speech of 51 children at the age 10-13 years interacting with Sony's pet robot Aibo.

Spontaneous, emotionally colored children's speech has been recorded via a close-talk microphone.

The audio recordings of the children have been segmented manually into small, syntactically meaningful 'chunks' using syntactic-prosodic criteria.

The data is annotated with 11 emotion categories by five human labelers on the word level.


The corpus consists of:

  • audio files (wav format, mono, 16bit, 16kHz) for the chunks,
  • German transliteration of the audio data,
  • corresponding German lexicon of all transcribed words,
  • information about the gender and the age of the children,
  • original emotion labels of the five human labelers for each word, and
  • one emotion label for the whole chunk.

For a detailed description of the FAU Aibo Emotion Corpus, please download my PhD thesis.