PERBANDINGAN MOTHER WAVELET UNTUK EKSTRAKSI CIRI ISYARAT TUTUR
نویسندگان
چکیده
Metode Wavelet merupakan salah satu metode yang unggul untuk menganalisis serta mengekstraksi ciri isyarat suara tutur. Dalam proses ekstraksi menggunakan Wavelet, terdapat beberapa faktor dapat berpengaruh dalam mendapatkan bersifat diskriminan, diantaranya: pemilihan mother wavelet, sub-band, dan level dekomposisi. Beberapa contoh sering digunakan Daubechies, Coiflet, Meyer, Haar, Symlet, Biortogonal. Pada penelitian ini dilakukan perbandingan berbagai macam efektif mengklasifikasi tutur, diharapkan melalui akan didapatkan terbaik paling cocok mengolah Tap filter pada masing-masing Mother rentang 1 hingga 10. Hasil tutur menunjukkan bahwa koefisien Daubechies 2 menghasilkan akurasi klasifikasi dibandingkan lainnya (Haar, Coiflet2, Biortogonal) suku kata konsonan hambat bahasa Indonesia ditunjukkan oleh hasil 90,6% (WPT+Daub2), 66,7% (WPT+Haar), 76,7% (WPT+Coif2), 62,3% (WPT+Meyer), 64,2% (WPT+Symlet), 61,7% (WPT+Biortogonal).
منابع مشابه
Perbandingan Shell Unix
Is it possible for an Information Technology [IT] product to be both mature and state-of-theart at the same time? In the case of the UNIX system, the answer is an unqualified "Yes." The UNIX system has continued to develop over the past twenty-five years. In millions of installations running on nearly every hardware platform made, the UNIX system has earned its reputation for stability and scal...
متن کاملPerformance Comparison of Enterprise Applications on Mobile Operating Systems
Seiring kemajuan dalam teknologi ponsel, Smartphone memiliki kemampuan untuk mengakses layanan web dalam aplikasi pengguna berinteraksi untuk mengambil dan mengirim informasi dari dan ke layanan web. Karenanya, Smartphone semakin meningkat popularitasnya. Pemanfaatan layanan web baru dan layanan web yang telah ada juga akan tumbuh pesat. Makalah ini memberikan perbandingan dari dua jenis utama ...
متن کاملThe X-Ray Transform Projection of 3D Mother Wavelet Function
As we all know, any practical computed tomography (CT) projection data more or less contains noises. Hence, it will be inconvenient for the postprocessing of a reconstructed 3D image even when the noise in the projection data is white. The reason is that the noise in the reconstructed image may be nonwhite. X-ray transform can be applied to the three dimensional (3D) CT, depicting the relations...
متن کاملApproximating i/o data using wavelet neural networks: control the position of mother wavelet
In this paper, we deal with the problem of function approximation from a given set of input/output data. This problem consists of analyzing training examples, so that we can predict the output of the model given new inputs. We present a new method for function approximation of the I/O data using Wavelet Neural Networks (WNN). This method is based on a new efficient method of optimizing the posi...
متن کاملMr Image Compression Based on Selection of Mother Wavelet and Lifting Based Wavelet
Magnetic Resonance (MR) image is a medical image technique required enormous data to be stored and transmitted for high quality diagnostic application. Various algorithms have been proposed to improve the performance of the compression scheme. In this paper we extended the commonly used algorithms to image compression and compared its performance. For an image compression technique, we have lin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: JIKO (Jurnal Informatika dan Komputer)
سال: 2022
ISSN: ['2656-1948', '2614-8897']
DOI: https://doi.org/10.26798/jiko.v6i2.554