Investigation of lexical f0 and duration patterns in French using large broadcast news speech corpora

نویسندگان

  • Rena Nemoto
  • Martine Adda-Decker
  • Jacques Durand
چکیده

This work aims at improving our knowledge of links between prosody and pronunciation variants in French. An original methodology is proposed to study prosodic regularities of French words via average f0 profiles, by making use of automatic processing and 13 hours of broadcast news speech. Investigated influential factors include word syllable length, duration, word-final schwa, parts of speech. The following questions are addressed: can specific lexical f0 profiles be measured automatically using large corpora? If so, how do they vary with respect to the cited influential factors? Results confirm the known tendency of word-final syllable accentuation. They also highlight some word-initial accentuation. Higher average f0 profiles are measured for increasing segment durations (locally decreasing speaking rate), but also for words ending with schwas. Future studies include phrase boundary annotation and the extension to a larger variety of speaking styles and languages.

برای دانلود رایگان 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

Word Boundaries in French: Evidence from Large Speech Corpora

The goal of this paper is to investigate French word segmentation strategies using phonemic and lexical transcriptions as well as prosodic and part-of-speech annotations. Average fundamental frequency (f0) profiles and phoneme duration profiles are measured using 13 hours of broadcast news speech to study prosodic regularities of French words. Some influential factors are taken into considerati...

متن کامل

The SpeakingInfluence of Style on Lexical f Profiles in French

This study presents a comparison of French lexical fundamental frequency (f0) profiles for different speaking styles using phonemic, syllabic and lexical transcriptions as well as partof-speech annotations. Three speaking styles (broadcast news, broadcast conferences and conversations) with over 20 hours of speech were used. Syllabic word length and POS were considered as influential factors. R...

متن کامل

An Analysis of Sentence Segmentation Features for Broadcast News, Broadcast Conversations, and Meetings

Information retrieval techniques for speech are based on those developed for text, and thus expect structured data as input. An essential task is to add sentence boundary information to the otherwise unannotated stream of words output by automatic speech recognition systems. We analyze sentence segmentation performance as a function of feature types and transcription (manual versus automatic) f...

متن کامل

Acoustic Differentiation of L- and L-L% in Switchboard and Radio News Speech

Acoustic evidence for a distinction between low-toned intermediate (ip) and intonational phrase (IP) boundaries is presented from two speech corpora representing spontaneous, conversational speech and scripted broadcast speech. Robust effects of the two boundary levels are found in the phrase-final syllable rime in both corpora. Nucleus duration is longer and the F0 value at rime end is lower a...

متن کامل

Une comparaison de la déclinaison de F0 entre le français et l'allemand journalistiques (F0-declination : a comparison between French and German journalistic speech) [in French]

F0-declination : a comparison between French and German journalistic speech The aim of the present study is to investigate F0-declination over the course of utterances in French and German journalistic speech by using large transcribed and automatically segmented corpora (a total of about 80,000 utterances of more than 1,000 speakers). Two different methods were applied : (i) regression-analysi...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010