Speech Prosody 2010

Chicago, IL, USA
May 10-14, 2010

Automatic Duration-Related Salience Detection in Brazilian Portuguese Read and Spontaneous Speech

Plínio A. Barbosa

Speech Prosody Studies Group/Dep. of Linguistics/Inst.Est. Ling., Univ. of Campinas, Brazil

This work presents an automatic prosodic salience detector algorithm which does not require the use of language-specific duration values. It is implemented in two steps: automatic detection of vowel onsets (VO) followed by the detection of normalized VO-to-VO duration peaks. The algorithm's performance is compared to that of a semi-automatic version. Perceived salience is also compared. For both fast and slower read speech, precision and accuracy of perceived word salience are between 61 and 80 %. In a larger corpus of read and storytelling speech, precision is generally higher than 70 %, whereas accuracy is higher than 80 % when the automatic version is compared with the semi-automatic one. The automatic algorithm's performance is found to be similar to that of the prominence detector reported in [1].

Index Terms: prominence detection, speech rhythm, duration


  1. Wang, D., Narayanan, S., "An acoustic measure for word prominence in spontaneous speech", IEEE Trans. ASLP, 15(2):690-701, 2007.

Full Paper

Bibliographic reference.  Barbosa, Plínio A. (2010): "Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech", In SP-2010, paper 067.