Skripsi

OPTIMASI POWER NORMALIZED CEPSTRAL COEFFICIENTS DAN GROWING SELF ORGANIZING MAPS DALAM PENGENALAN SUARA

---

Penilaian

---

Speech recognition system is a technology that allows devices to recognize words by digitizing words and matching digital signals with certain patterns stored in computer devices. The purpose of this study is to develop a speech recognition technique by implementing the Power Normalized Cepstral Coefficients for feature extraction method and classifying it using the Self Organizing Maps and Growing Self Organizing Maps methods. Model analysis technique is using the Confusion Matrix. The dataset is used in the form of voice data taken manually with a total of 200 voice data from 20 respondents. The results of this analysis obtained several conclusions, the first Power Normalized Cepstral Coefficients method is able to make voice data that has noise become a good feature for training and testing. The second, methods of Growing Self Organizing Maps is able to produce the same accuracy as the method of Self Organizing Maps with a smaller number of iterations and final weight nodes than the Self Organizing Maps method requires. The third, the spread factor value has an influence to form the right model by determining the growth of nodes. The fourth, Self Organizing Maps and Growing Self Organizing Maps are both capable of producing good models in terms of model performance measurement with the support of the Power Normalized Cepstral Coefficients feature achieving an accuracy of 95%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107004729	T55117	T551172021	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T551172021

Publisher

Inderalaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer., 2021

Collation

xv, 78 hlm. : ilus. ; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Magister Ilmu Komputer
Kecerdasan Buatan-Power Normalized

Specific Detail Info

-

Statement of Responsibility

DS

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment