Fiche du document
13 octobre 2022
- handle: 10670/1.vbhr1u
- hal: hal-01414600
http://hal.archives-ouvertes.fr/licences/publicDomain/ , info:eu-repo/semantics/OpenAccess
Mots-clés
annotation speech image corpusSujets proches
Natural science Sciences Science of science Pictorial data processing Picture processing Processing, Image Human faceCiter ce document
Brigitte Bigi, « SPPAS - the automatic annotation and analysis of speech (version 4.7) », HAL-SHS : sciences de l'information, de la communication et des bibliothèques, ID : 10670/1.vbhr1u
Métriques
Partage / Export
Résumé
SPPAS is a robust and reliable software for the automatic annotation, for the analyses of annotated-data and to convert annotated files.As the primary functionality, SPPAS proposes a set of automatic or semi-automatic annotations of recordings: Momel: modelling melody, INTSINT: Intonation, Search for IPUs: speech/silence segmentation, Fill in IPUs: search for IPUs and fill in the IPUs with a transcription, Text normalization, Phonetization: grapheme to phoneme conversion, Alignment: phonetic segmentation, Syllabification: group phonemes into syllables, Time Group Analyzer, Self-Repetitions detection, Other-repetitions detection, Re-occurrences, Detection of lexical repetitions of a speaker, Face detection (image processing), Person Face identity (image processing), Face landmark (image processing).