SegProso

SegProso is a Praat-based tool for the automatic segmentation of speech corpora into prosodic units:

• syllables

  • stress groups (SG)

  • intonation groups (IG)

  • breath groups (BG)

SegProso is currently available for Catalan, Spanish, Brazilian Portuguese and French. Other languages can be added with minimum or none adaptation of the scripts.

The tool uses a full rule and knowledge-based approach to perform the boundary detection tasks.

SegProso is available for public download from here.

Input

SegProso needs as input two files:

• • A wav fie countaining the utterance to be annotated

  • A TextGrid file containing at least two tiers:

    • • the orthographic transcription of the utterance word-by-word

      • the phone segmentation in SAMPA or IPA format

Output

Its output is the same input TextGrid file enriched with four new tiers, containing the segmentation of the four annotated prosodic units.