Skripsi

PREDIKSI GERAKAN BAHASA ISYARAT BERDASARKAN SUARA MENGGUNAKAN HIDDEN MARKOV MODEL

---

Communication is very important for humans in their daily lives. However, for people with hearing impairments, this can be a problem. Many people do not understand the sign language used by people with hearing impairments. In order to communicate with people with hearing impairments, people must learn sign language. Therefore, a system that predicts sign language movements based on sound can help people learn sign language movements. The Hidden Markov Model (HMM) is a model used to recognize sounds. This choice was made because this model produced good results on a dataset with characteristics similar to the dataset used in this study. Mel Frequency Cepstral Coefficients (MFCC) were used as a method for feature extraction before training with the Hidden Markov Model (HMM). Four HMM models were created with different n_components parameter configurations. The model trained by augmenting the dataset with noise and stretch, consisting of 684 data points, split 90:10, and an n_components value of 45, was the best model with a result of 71.35%.

---

Availability

Detail Information

Series Title

-

Call Number

T1897992025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 112 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.320 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Pengenalan Pola--Suara

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment