Summary of the paper

Title Word Boundaries in French: Evidence from Large Speech Corpora
Authors Rena Nemoto, Martine Adda-Decker and Jacques Durand
Abstract The goal of this paper is to investigate French word segmentation strategiesusing phonemic and lexical transcriptions as well as prosodic andpart-of-speech annotations. Average fundamental frequency (f0) profiles andphoneme duration profiles are measured using 13 hours of broadcast news speechto study prosodic regularities of French words. Some influential factors aretaken into consideration for f0 and duration measurements: word syllablelength, word-final schwa, part-of-speech. Results from average f0 profilesconfirm word final syllable accentuation and from average duration profiles, wecan observe long word final syllable length. Both are common tendencies inFrench. From noun phrase studies, results of average f0 profiles illustratehigher noun first syllable after determiner. Inter-vocalic duration profileresults show long inter-vocalic duration between determiner vowel and precedingword vowel. These results reveal measurable cues contributing to word boundarylocation. Further studies will include more detailed within syllable f0patterns, other speaking styles and languages.
Language Knowledge Discovery/Representation
Topics Prosody, Speech resource/database, Knowledge Discovery/Representation
Full paper Word Boundaries in French: Evidence from Large Speech Corpora
Bibtex @InProceedings{NEMOTO10.386,
  author = {Rena Nemoto, Martine Adda-Decker and Jacques Durand},
  title = {Word Boundaries in French: Evidence from Large Speech Corpora},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA