recognition is a computing task of validating a user’s claimed identity using
characteristics extracted from their voice. This technique is one of the most
useful and popular biometric recognition techniques in the world especially
related areas in which security is a major concern. It can be used for
authentication, surveillance forensic speaker recognition and a number of
related activities. Our proposed project work consists of
truncating a recorded voice signal, framing it ,passing it through a
window function calculating the FFT, extracting
its features and matching it with a stored data. Mel frequency cepstral
coefficients (MFCC) are applied for feature extraction purpose. Gaussian
mixture modeling (GMM) algorithms are used for feature matching purpose.
The developed system uses the LabVIEW (Laboratory Virtual Instrument
Engineering Workbench) 2014 platform.
processing; MFCC; GMM; LabVIEW.
Speaker recognition is
the process of automatically recognizing who is speaking on the basis of
individual information included in speech signals.It can be divided into
speaker identification and speaker verification.speaker identification
determines which registered speaker provides a given utterance from amongst a
set of known speakers.speaker verification accepts or rejects the identity
claim of a speaker.
The process of
Speaker recognition consists of two modules namely: – feature extraction and
feature matching. Feature extraction is the process in which we extract a small
amount of data from the voice signal that can later be used to represent each
speaker. Feature matching involves identification of the unknown speaker by
comparing the extracted features from his/her voice input with the ones from a
set of known speakers.MFCC method is used for feature extraction and GMM method
is used for feature matching module.
The speaker verification
is the user has to tell the system, who he /she claims to be.Then ,the system
compares the stored pattern of the claimed user with the new pattern of the
unknown user and answers ‘accept’ or ‘reject’.Hence , a one to one comparision
phases of the speech signal processing are recording the human voice signal and
pre-processing the signal .
Low pass filter is a filter that
passes signals with a frequency lower than a certain cutoff frequency and
attenuates signals with frequencies higher than the cutoff frequency.
Sampling frequency of
speech signal is 8kHz.
The recorded discrete
signal has always a finite length Ntotal,but
is usually not processed whole.The signal is framed-cut into pieces.Length of
one frame is N<