Thesis Details
Voice Dialog System in Web Browser for Demonstration Purposes
This thesis describes how to prepare and design a voice-controlled assistant(voicebot), which can be deployed on any website as a modern way to communicate with customers using internet browsers. The main emphasis is put on synchronization between voice dialog and the graphical interface of the website. The synchronization can be achieved by transferring bidirectional voice and text commands between client and server. This is achieved by using WebRTC technology with SIP as a signaling protocol. The thesis deals with a wide range of protocols and technologies as well as interconnecting VoIP telephony, computer networks, and Phonexia speech technologies based on machine learning. As a result, deployment of the voicebot can reduce costs on outgoing calls, ease agents of a FAQ burden, and increase customers' interest in the product/company.
voicebot, WebRTC, SIP, RTP, SDP, Asterisk, voice dialogue system, NAT traversing, Phonexia, speech recognition, internet browser, IBM Watson, WebSocket, Phonexia Speech Engine
Kolář Dušan, doc. Dr. Ing. (DIFS FIT BUT), člen
Lengál Ondřej, Ing., Ph.D. (DITS FIT BUT), člen
Očenášek Pavel, Mgr. Ing., Ph.D. (DIFS FIT BUT), člen
Polčák Libor, Ing., Ph.D. (DIFS FIT BUT), člen
Veselý Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
@mastersthesis{FITMT23460,
author = "Pavol Vl\v{c}ek",
type = "Master's thesis",
title = "Voice Dialog System in Web Browser for Demonstration Purposes",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2021,
location = "Brno, CZ",
language = "english",
url = "https://www.fit.vut.cz/study/thesis/23460/"
}