Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Burst Detection Based on Measurements of Intensity Discrimination

John-Paul Hosom (1), Ronald A. Cole (2)

(1) Center for Spoken Language Understanding (CSLU), Oregon Graduate Institute of Science and Technology (OGI), Portland, OR, USA
(2) Center for Speech and Language Research (CSLR), University of Colorado, Boulder, Boulder, CO, USA

Detection of burst-related impulses, such as those accompanying plosive stop consonants, is an important problem for accurate measurement of acoustic features for recogntion (e.g., voice-onset-time) and for accurate automatic phonetic alignment. The proposed method of burst detection utilizes techniques for identifying and combining information about specific acoustic characteristics of bursts. One key element of the proposed method is the use of a measurement of intensity discrimination based on models from perceptual studies. Our experiments compared the proposed method of burst detection to the support vector machine (SVM) method, described below. The total error rate for the proposed method is 13.2% on the test-set partition of the TIMIT corpus, compared to a total error rate of 24% for the SVM method.


Full Paper

Bibliographic reference.  Hosom, John-Paul / Cole, Ronald A. (2000): "Burst detection based on measurements of intensity discrimination", In ICSLP-2000, vol.4, 564-567.