Pengenalan Ucapan Menggunakan Hibrida Jaringan Syaraf Tiruan Hidden Markov Model untuk Simulasi Layanan Pelanggan Lewat Telepon  

Oleh:

Putri, Frederica Pingkan A. ; Lukas

Jenis: Article from Journal - ilmiah nasional - tidak terakreditasi DIKTI - atma jaya
Dalam koleksi: Metris: Jurnal Mesin, Elektro, Industri dan Sains vol. 8 no. 2 (Sep. 2007), page 168-174.
Topik: Jaringan Syaraf Tiruan; Model Markov Tersembunyi; Koefisien Cepstral
Fulltext: Frederica Pingkan, Lukas-Bernard.pdf (6.86MB)

Isi artikel

Speech recognition is one of the challenging technology systems, since it will significantly ease accessing any task also electronic equipment Hybrid NN/HMM modeling is nowadays an established alternative approach in automatic speech recognition technology. Researcher is continuing to develop the method because of its supremacy to overrun the acoustic problem. This statistical based method processes cepstral coefficient which is the main factor represents characterictic of each speech data. This paper introduces one of speech recognition aplication technique that will be able to identify number in Indonesian language for Simulation of Customer Service by Phone, using a microphone Based on the test results, various way of speaking in training the data increase the system ability in speech recognition

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali