TY - JOUR
T1 - An investigation into front-end signal processing for speaker normalization
AU - Umesh, S.
AU - Sinha, Rohit
AU - Sriperumbudur, Bharath Kumar
PY - 2004
Y1 - 2004
N2 - Our investigation into the front-end signal processing for maximum likelihood based speaker normalization reveals that in the linear scaling model, it is more appropriate (and evidently more correct) to assume that the spectral envelopes of any two speakers for same sound are linearly scaled versions of one and another, rather than assuming that the whole magnitude spectra (including pitch harmonics) are scaled. The use of the proposed model and its implementation results in about 4% and 7% relative improvement for adults and children respectively on a digit recognition task.
AB - Our investigation into the front-end signal processing for maximum likelihood based speaker normalization reveals that in the linear scaling model, it is more appropriate (and evidently more correct) to assume that the spectral envelopes of any two speakers for same sound are linearly scaled versions of one and another, rather than assuming that the whole magnitude spectra (including pitch harmonics) are scaled. The use of the proposed model and its implementation results in about 4% and 7% relative improvement for adults and children respectively on a digit recognition task.
UR - http://www.scopus.com/inward/record.url?scp=4544318501&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=4544318501&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:4544318501
SN - 1520-6149
VL - 1
JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ER -