TY - JOUR
T1 - Automatic recognition of pitch movements using multilayer perception and time-delay recursive neural network
AU - Kim, Sung Sunk
AU - Hasegawa-Johnson, Mark
AU - Chen, Ken
N1 - Funding Information:
Manuscript received May 18, 2003; revised November 21, 2003. This work was supported the NSF under Award 0132900 and by a grant from the University of Illinois Critical Research Initiative. Statements in this letter reflect the opinions and conclusions of the authors and are not endorsed by the NSF or the University of Illinois. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Alex Acero.
PY - 2004/7
Y1 - 2004/7
N2 - This letter demonstrates hidden Markov model (HMM), multilayer perceptron (MLP), and time-delay recursive neural network (TDRNN) architectures for the purpose of recognizing pitch accents given observation of the F0 and energy trajectories. At an insertion error rate of 25%, the deletion error rates of the MLP, TDRNN, and HMM are 13.2%, 7.9%, and 32.7%, respectively, despite the fact that both MLP and TDRNN have 70% fewer trainable parameters than the HMM. Error analysis suggests that low-pitch accents may require long-term context to correctly recognize, while high-pitch accents may be recognizable based on local pitch contour.
AB - This letter demonstrates hidden Markov model (HMM), multilayer perceptron (MLP), and time-delay recursive neural network (TDRNN) architectures for the purpose of recognizing pitch accents given observation of the F0 and energy trajectories. At an insertion error rate of 25%, the deletion error rates of the MLP, TDRNN, and HMM are 13.2%, 7.9%, and 32.7%, respectively, despite the fact that both MLP and TDRNN have 70% fewer trainable parameters than the HMM. Error analysis suggests that low-pitch accents may require long-term context to correctly recognize, while high-pitch accents may be recognizable based on local pitch contour.
UR - http://www.scopus.com/inward/record.url?scp=3142765506&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=3142765506&partnerID=8YFLogxK
U2 - 10.1109/LSP.2004.830114
DO - 10.1109/LSP.2004.830114
M3 - Article
AN - SCOPUS:3142765506
SN - 1070-9908
VL - 11
SP - 645
EP - 648
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
IS - 7
ER -