Speaker identification using multilayer perceptrons and radial basis function networks

Man Wai Mak; W. G. Allen; G. G. Sexton

doi:10.1016/0925-2312(94)90036-1

Speaker identification using multilayer perceptrons and radial basis function networks

Man Wai Mak, W. G. Allen, G. G. Sexton

Research output: Journal article publication › Journal article › Academic research › peer-review

27 Citations (Scopus)

Abstract

This paper compares the Multilayer Perceptrons network (trained by the backpropagation algorithm) and the Radial Basis Function networks in the task of speaker identification. The experiments were carried out on 200 utterances (10 digits) of 10 speakers. LPC-derived cepstrum coefficients were used as the speaker specific features. The results showed that the Multilayer Perceptrons networks were superior in memory usage and classification time. However, they suffered from long training time and the error rate was slightly higher than that of Radial Basis Function networks.

Original language	English
Pages (from-to)	99-117
Number of pages	19
Journal	Neurocomputing
Volume	6
Issue number	1
DOIs	https://doi.org/10.1016/0925-2312(94)90036-1
Publication status	Published - 1 Jan 1994
Externally published	Yes

Keywords

backpropagation
Multilayer Perceptrons
Neural networks
pattern recognition
Radial Basis Function
speaker recognition
speech processing

ASJC Scopus subject areas

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

More information

10.1016/0925-2312(94)90036-1

Cite this

@article{d79e87607312426ba95925b6261bdb60,

title = "Speaker identification using multilayer perceptrons and radial basis function networks",

abstract = "This paper compares the Multilayer Perceptrons network (trained by the backpropagation algorithm) and the Radial Basis Function networks in the task of speaker identification. The experiments were carried out on 200 utterances (10 digits) of 10 speakers. LPC-derived cepstrum coefficients were used as the speaker specific features. The results showed that the Multilayer Perceptrons networks were superior in memory usage and classification time. However, they suffered from long training time and the error rate was slightly higher than that of Radial Basis Function networks.",

keywords = "backpropagation, Multilayer Perceptrons, Neural networks, pattern recognition, Radial Basis Function, speaker recognition, speech processing",

author = "Mak, {Man Wai} and Allen, {W. G.} and Sexton, {G. G.}",

year = "1994",

month = jan,

day = "1",

doi = "10.1016/0925-2312(94)90036-1",

language = "English",

volume = "6",

pages = "99--117",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Speaker identification using multilayer perceptrons and radial basis function networks

AU - Mak, Man Wai

AU - Allen, W. G.

AU - Sexton, G. G.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - This paper compares the Multilayer Perceptrons network (trained by the backpropagation algorithm) and the Radial Basis Function networks in the task of speaker identification. The experiments were carried out on 200 utterances (10 digits) of 10 speakers. LPC-derived cepstrum coefficients were used as the speaker specific features. The results showed that the Multilayer Perceptrons networks were superior in memory usage and classification time. However, they suffered from long training time and the error rate was slightly higher than that of Radial Basis Function networks.

AB - This paper compares the Multilayer Perceptrons network (trained by the backpropagation algorithm) and the Radial Basis Function networks in the task of speaker identification. The experiments were carried out on 200 utterances (10 digits) of 10 speakers. LPC-derived cepstrum coefficients were used as the speaker specific features. The results showed that the Multilayer Perceptrons networks were superior in memory usage and classification time. However, they suffered from long training time and the error rate was slightly higher than that of Radial Basis Function networks.

KW - backpropagation

KW - Multilayer Perceptrons

KW - Neural networks

KW - pattern recognition

KW - Radial Basis Function

KW - speaker recognition

KW - speech processing

UR - http://www.scopus.com/inward/record.url?scp=0028381973&partnerID=8YFLogxK

U2 - 10.1016/0925-2312(94)90036-1

DO - 10.1016/0925-2312(94)90036-1

M3 - Journal article

SN - 0925-2312

VL - 6

SP - 99

EP - 117

JO - Neurocomputing

JF - Neurocomputing

IS - 1

ER -

Speaker identification using multilayer perceptrons and radial basis function networks

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this