Mel Frequency Cepstral Coefficients (MFCC) based speaker identification in noisy environment using wiener filter

Chauhan, Paresh M.; Desai, Nikita

doi:10.1109/icgccee.2014.6921394

Cited by 35 publications

(25 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Modifikasi metode MFCC menggunakan residu deteksi endpoint didasarkan pada Spectral Subtraction (SS) [13] dan penelitian Paresh dan Nikita [4]. Metode Spectral Subtraction menghilangkan derau berdasarkan informasi yang didapatkan dari beberapa frame awal.…”

Section: Metode Yang Diusulkanunclassified

“…Metode Spectral Subtraction menghilangkan derau berdasarkan informasi yang didapatkan dari beberapa frame awal. Sedangkan Paresh dan Nikita menghilangkan derau menggunakan Wiener filter yang diletakkan di domain frekuensi (setelah FFT) [4].…”

Section: Metode Yang Diusulkanunclassified

“…Hasilnya digunakan untuk mengurangi magnitude frekuensi sinyal utama. Pengurangan ini terjadi di domain frekuensi seperti penelitian Paresh dan Nikita yang menghilangkan derau menggunakan Wienar filter di domain frekuensi [4].…”

Section: Metode Yang Diusulkanunclassified

“…Peneliti lainnya yang mencoba menghilangkan derau pada MFCC adalah Paresh M. Chauhan dan Nikita P. Desai [4]. Paresh M. Chauhan dan Nikita P. Desai menambahkan Wiener filter setelah proses FFT.…”

unclassified

“…Residu algoritma deteksi endpoint diubah ke domain frekuensi sehingga didapatkan magnitude frekuensi derau. Magnitude tersebut kemudian digunakan untuk menghilangkan derau pada speech di domain frekuensi seperti yang dilakukan pada penelitian Paresh M. Chauhan dan Nikita P. Desai [4].…”

unclassified

See 4 more Smart Citations

Identifikasi Parameter Optimal Gaussian Mixture Model Pada Identifikasi Pembicara Di Lingkungan Berderau Menggunakan Residu Deteksi Endpoint

Prayogi¹,

Buliali²

2015

JUTI

View full text Add to dashboard Cite

ABSTRAK ABSTRACT One of the problems in the speaker identification system is a feature that generated less resistant to noise. In the noisy environment, the speaker identification system performance can drop significantly. It is caused by environmental differences when training and testing. One feature extraction method used to identify the speaker and sensitive to noise is Mel frequency cepstral coefficient (MFCC). In a clean environment, the performance generated by MFCC method is very high, but dropped dramatically when in the noisy environment. In this study, we propose to modify the MFCC method using endpoint detection residues. Results of endpoint detection algorithm is speech and nonspeech (residue). Nonspeech or residues are usually not used in the next process. At the noisy signal, the residue of endpoint detection algorithm is filled by the noise itself so that it can be used as information noise. The residue is extracted to get the magnitude of the noisy signal. Magnitude of the noisy signal is used to remove noise on the main signal or speech.The experiments using five types of noise with seven levels of SNR. The type of noise that used is f16, hfchannel, pink, volvo, and white. While the level of SNR that used is clean, 25, 20, 15,10,5, and

show abstract

Section: Metode Yang Diusulkanunclassified