La liaison dans la parole spontanée familière : explorations semi-automatiques de grands corpus (French Liaison in casual speech : automatic and manual investigations) [in French]

نویسندگان

  • Martine Adda-Decker
  • Elisabeth Delais-Roussarie
  • Cécile Fougeron
  • Cédric Gendrot
  • Lori Lamel
چکیده

French Liaison in casual speech : automatic and manual investigations The realisation of the French Liaison is investigated in a large corpus of casual speech. Considering that casual speech gives rise to a large range of pronunciation variants and that overall temporal reduction increases (word and phone duration measurements) as compared to read and prepared speech, one may hypothesize that French liaison tends to be less productive in this kind of speaking style. We made use of automatic speech alignments to evaluate optional liaison realisations in potential liaison sites (word ending in a liaison consonant followed by a word-initial (semi)-vowel). Speech comes from the NCCFr corpus including 46 mostly young speakers with a total of more than 30 hours of speech. Realized liaisons were examined and measured for the most frequent liaison consonants (/z/, /n/ and /t/) as a function of a classification of the sites as mandatory, optional or forbidden with respect to liaison realization. An original contribution investigates liaison realization as a function of a speaker-dependent speech rate measure. MOTS-CLÉS : Variantes de prononciation, liaison, parole familière, réduction temporelle.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Using automatic speech processing to study French oral vowels

RÉSUMÉ. Le traitement automatique de la parole peut concrètement contribuer à éclairer de nombreuses questions concernant la variabilité phonémique à l’oral. L’exploitation de grandes masses de données permet ainsi de dégager de grandes tendances, dont une interprétation plus fine repose ensuite à la fois sur un éclairage linguistique et sur un certain nombre de précautions méthodologiques. Nou...

متن کامل

Contexte et nature des réalisations phonétiques en parole conversationnelle (Context and nature of phonetic realizations in conversational speech) [in French]

________________________________________________________________________________________________________ Context and nature of phonetic realizations in conversational speech Since a decade, research in phonetics has turned with interest to the description of large corpora of casual speech. This new field of research opens up many opportunities but asks also new questions for phoneticians. First...

متن کامل

Vers une annotation automatique de corpus audio pour la synthèse de parole (Towards Fully Automatic Annotation of Audio Books for Text-To-Speech (TTS) Synthesis) [in French]

RÉSUMÉ La construction de corpus de parole est une étape cruciale pour tout système de synthèse de la parole à partir du texte. L’usage de modèles statistiques nécessite aujourd’hui l’utilisation de corpus de très grande taille qui doivent être enregistrés, transcrits, annotés et segmentés afin d’être exploitables. La variété des corpus nécessaire aux applications actuelles (contenu, style, etc...

متن کامل

Investigating syllabic structures and their variation in spontaneous French

The paper presents a study of syllabic structures and their variation in a large corpus of French radio interview speech. A further aim is to show how automatic speech recognition (ASR) systems can serve as a linguistic tool to consistently explore virtually unlimited speech corpora. Automatically selected subsets can be manually checked to accumulate knowledge on pronunciation variants. Our be...

متن کامل

Pronunciation variants across system configuration, language and speaking style

This contribution aims at evaluating the use of pronunciation variants for di erent recognition system con gurations, languages and speaking styles. This study is limited to the use of variants during speech alignment, given an orthographic transcription of the utterance and a phonemically represented lexicon, and is thus focused on the modeling capabilities of the acoustic word models. To meas...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012