In recent years, the development of bots such as chatbot, and then later, voicebot has enabled the replacement of manual call operations in many corporations since they can execute calls automatically. To prepare for the calls in automated call centers using voicebot applications, one of the critical procedures is to convert text script into human-like voices. In this context, the text-to-speech (TTS) application plays a crucial role as it is the essential element in the system that brings the automated call centers' success.

This tutorial aims to introduce text-to-speech and its applications in daily life. The tutorial will also discuss several aspects such as model selection, data preparation, and language processing since they directly affect the developed TTS application's overall quality.

Speaker

Tran Duc Chung - PhD, FPT University, Vietnam

Tran Duc Chung completed bachelor and Ph. D. degrees in Electrical & Electronic Engineering at PETRONAS University of Technology, Malaysia, in 2014 and 2018.

Before joining FPT University, Hanoi, Vietnam, he had worked for several companies, namely Intel Technology Sdn. Bhd. Malaysia, R&D Centre - Sony EMCS Sdn. Bhd. Malaysia, Dasan Zhone Solutions Vietnam.

At FPT Technology Research Institute, Vietnam, he gained substantial experience researching text-to-speech (TTS) engine development.

He is currently interested in researching emerging technologies and topics, including Natural Language Processing and Generation (NLP, NLG) and Applied Artificial Intelligence.

Moderator

Stanislav Eroshenko - Senior Lecturer at Ural Power Engineering Institute of Ural Federal University, Vice-Chairman of the CIGRE Next Generation Network Executive Committee.

The event will take place online.

Registration is required.

The language of the lecture is English!