Speaker recognition using MFCC, shifted MFCC with vector quantization and fuzzy

Abstract

In the range of biometric we consider the variability of discourse flag because of the vicinity of clam or which impressively corrupts the productivity of ASR in genuine ecological condition. Speaker-vocal attributes exist in discourse signals and because of distinctive resonances of diverse speakers speaker acknowledgment framework checks the speaker. These distinctions can be misused by extricating element vectors like Mel-Frequency Cepstral Coefficient (MFCCs) from the discourse signal. In this paper we have utilized MFCC and Shifted MFCC with Vector Quantization and fuzzy demonstrating strategies correspondingly to enhance the execution of ASR even in boisterous environment with the assistance of redesigned discourse data which are available at high recurrence in otherworldly area. The mix of fuzzy demonstrating and shifted MFCC makes an in number total calculation which has the sensibly high vigour to clamour. In exploratory results, we have discovered 10-20% upgraded precision even at 5-8dB SNR in the vicinity of music foundation, boisterous natural condition furthermore in the vicinity of repetitive sound.

Development of Quranic Reciter Identification System using MFCC and GMM Classifier

“…373 nearest neighbors, vector quantization [6], hidden Markov model (HMM) [9], Gaussian mixture model (GMM) [10], artificial neural network [4], and deep neural network (DNN) [11]. Of the various classifiers available, in this research we selected GMM as our baseline for speaker recognition.…”

“…The front-end may also include pre-processing modules, such as voice activity detection to remove silence from the input, or a channel compensation module to normalize the effect of the recording channel [5], [13]. Currently, there are many methods that can be used to verify a speaker identity and the most two known methods are linear predictive coding (LPC) and Mel frequency cepstrum (MFCC) [4], [6]. However, in this paper MFCC methods is choosen as the feature extraction since the system give higher accurancy.…”

“…Many features and classifiers have been used in the speaker recognition research. Audio features such as Mel-frequency Cepstral Coefficients [4], [6], linear-frequency cepstral coefficients (LFCC), and linear predictive coefficients (LPC). LFCC is similar to MFCC except that their frequencies is not warped by a nonlinear frequency scale and it has been found that LFCC performed better than MFCC in female trials [7].…”

Wavelets for Speaker Recognition Using GMM Classifier

“…The Bangla words and speaker are recognized by MFCC. The utilization of MFCC and Shifted MFCC features are discussed in [8] for speaker recognition. To enhance the execution at a high recurrence area, fuzzy demonstrating strategies and vector quantization are used.…”

Performance of speaker recognition system using shifted mfcc, delta spectral cepstral coefficient (DSCC) and Fuzzy techniques

“…FCM represents an unsupervised form of clustering in an extensive multidimensional space. Bansal P.(2015) prove that decision-making ability of fuzzy c means clustering depends upon the grade of similarity and membership function. Susan S. (2012) proves that FCM greatly provides low error valuation by means of mean square error (MSE).…”