Title :
An Unsupervised Quantitative Measure for Word Prominence in Spontaneous Speech
Author :
Wang, Dagen ; Narayanan, Shrikanth
Author_Institution :
Speech Anal. & Interpretation Lab., USC Viterbi Sch. of Eng., Los Angeles, CA, USA
Keywords :
computational linguistics; correlation methods; natural languages; speech processing; POS linguistic correlation; acoustic feature set fusion; acoustic modeling; automatic speech prominence detection; content word classes; continuous prominence score; function word classes; natural language understanding; part of speech; prosodic properties; speech signal correlation envelope; spontaneous speech; unsupervised quantitative word prominence measure; Acoustic measurements; Acoustic signal detection; Acoustical engineering; Automatic speech recognition; Natural languages; Robustness; Speech analysis; Speech processing; Tagging; Viterbi algorithm;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415129