Model Identifikasi Kata Ucapan Tuna Wicara

Abstract

Speech impaired is the inability of someone to speak, even though speaking ability is important in order to communicate with other people. Dealing with this as someone who has speech impairments has their own way of communicating, namely by using sign language, but not everyone understands the sign language. The MFCC and Backpropagation ANN methods are implemented on a Single Board Computer (SBC) designed to overcome speech impaired communication problems. The MFCC method is used to retrieve the features of speech impairment and the Backpropagation ANN is used for sound pattern recognition.The system was trained using 750 sound samples consisting of 5 speakers, each uttering as many as 30 repetitions of the pronunciation of words (makan, kamar, kerja, harga and lapar), then tested using 125 sound samples consisting of 5 speakers, each saying 5 repetitions of words. Training and testing of Backpropagation ANN using input coefficients generated from MFCC. The results showed that the MFCC and Backpropagation ANN methods were able to identify speech words with 60% accuracy, 40% precision and 40% sensitivity.

Penanganan Anak Tunawicara : Studi Kasus

“…Hal ini disebabkan organ vokal seperti rongga mulut, langit-langit mulut, lidah, dan pita suara hilang atau tidak berfungsi dengan baik. Selain itu, terdapat perkembangan bahasa yang terlambat, pendengaran yang terganggu, sistem saraf dan struktur otot yang rusak (Wiranda & Putro, 2019).…”

Media Pembelajaran Fingerspelling Alphabet untuk Penderita Tunarungu dan Tunawicara Berbasis Android

“…Selain itu juga adanya kekurangan pada indra pendengaran, keterlambatan perkembangan bahasa, kerusakan pada sistem syaraf dan struktur otot. (Wiranda and Putro, 2019) 3. METODE PENELITIAN 3.1.…”