Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 1022420090010020015
Phonetics and Speech Sciences
2009 Volume.1 No. 2 p.15 ~ p.22
Prominence Detection Using Feature Differences of Neighboring Syllables for English Speech Clinics
Shim Sung-Geon

You Ki-Sun
Sung Won-Yong
Abstract
Prominence of speech, which is often called ¡¯accent,¡¯ affects the fluency of speaking American English greatly. In this paper, we present an accurate prominence detection method that can be utilized in computer-aided language learning (CALL) systems. We employed pitch movement, overall syllable energy, 300-2200 Hz band energy, syllable duration, and spectral and temporal correlation as features to model the prominence of speech. After the features for vowel syllables of speech were extracted, prominent syllables were classified by SVM (Support Vector Machine). To further improve accuracy, the differences in characteristics of neighboring syllables were added as additional features. We also applied a speech recognizer to extract more precise syllable boundaries. The performance of our prominence detector was measured based on the Intonational Variation in English (IViE) speech corpus. We obtained 84.9% accuracy which is about 10% higher than previous research.
KEYWORD
Prominence detection, Speech clinic
FullTexts / Linksout information
Listed journal information
ÇмúÁøÈïÀç´Ü(KCI)