MULYO, MAHESA ANUGRAH (2022) SISTEM APLIKASI VIDEO CONFRENCE DENGAN NOTULENSI MENGGUNAKAN METODE SPEECH RECOGNITION BERBASIS WEB. Undergraduate thesis, Universitas Stikubank.
![[thumbnail of HALAMAN JUDUL]](/style/images/fileicons/application_pdf.png) |
PDF (HALAMAN JUDUL)
Download (754kB) |
|
PDF (ABSTRAK)
Download (218kB) |
|
PDF (BAB I)
Download (93kB) |
|
PDF (BAB II)
Restricted to Repository staff only Download (80kB) |
|
PDF (BAB III)
Restricted to Repository staff only Download (408kB) |
|
PDF (BAB IV)
Restricted to Repository staff only Download (324kB) |
|
PDF (BAB V)
Restricted to Repository staff only Download (140kB) |
|
PDF (BAB VI)
Restricted to Repository staff only Download (32kB) |
|
PDF (DAFTAR PUSTAKA)
Download (34kB) |
|
PDF (LAMPIRAN)
Restricted to Repository staff only Download (550kB) |
Abstract
Speech Recognition merupakan proses identifikasi suara berdasarkan kata yang diucapkan dengan melakukan konversi sebuah sinyal akustik, yang ditangkap oleh perangkat input suara serta dikonversi ke dalam bentuk digital print. Speech recognition menggunakan sistem algoritma komputer untuk menginterpretasi dan memproses ucapan lisan untuk kemudian mengubahnya ke dalam bentuk tulisan. Speech recognition bekerja dengan mengidentifikasi ucapan atau perkataan lisan pengguna agar dapat diinterpretasikan ke dalam format tertulis. Banyak metode yang bisa digunakan untuk pengenalan suara itu sendiri, salah satunya adalah metode Hidden Markov Model, metode ini berupa model statistika dari rantai markov. Hidden Markov Model merupakan perluasan dari rantai Markov di mana statenya tidak dapat diamati secara langsung (tersembunyi), tetapi hanya dapat diobservasi melalui suatu himpunan pengamatan lain. Algoritma ini digunakan sebagai teknik dasar untuk automatic speech recogition. Salah satu implementasi speech recognition menggunakan metode hidden markov model untuk aplikasi otomasi notulensi dari kegiatan video conference yang bisa merekam suara yang terjadi antar penggguna kemudian mengkonversinya dalam bentuk format dokumenseperti bentuk pdf atau doc. Speech Recognition is a voice identification process based on spoken words by converting an acoustic signal, which is captured by a voice input device and converted into digital print. Speech recognition uses a computer algorithm system to interpret and process spoken speech and then convert it into written form. Speech recognition works by identifying the user's spoken speech or speech so that it can be interpreted into a written format. Many methods can be used for speech recognition itself, one of which is the Hidden Markov Model method, this method isa statistical model of the Markov chain. Hidden Markov Model is an extension of the Markov chain where the state cannot be observed directly (hidden), but can only be observed through a set of other observations. This algorithm is used as the basic technique for automatic speechrecognition. One of the implementations of speech recognition using the hidden markov model method for automated application of minutes from video conference activities that can record sounds that occur between users and then convert them in the form of document formats such as pdf or doc forms.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Additional Information: | SKR.I.05.01.2209 NIM.18.01.53.0031 |
| Uncontrolled Keywords: | notulensi, speech recognition, video conference, Hidden Markov Model. notes, speech recognition, video conference, Hidden Markov Model |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Faculty / Institution: | Fakultas Teknologi Informasi > Program Studi Teknik Informatika |
| Depositing User: | Teteh Hayati |
| Date Deposited: | 27 Sep 2022 03:31 |
| Last Modified: | 27 Sep 2022 03:31 |
| URI: | https://eprints.unisbank.ac.id/id/eprint/8721 |
Actions (login required)
 |
View Item |
