Development and testing of an fpt.Ai-based voicebot

In recent years, voicebot has become a popular communication tool between humans and machines. In this paper, we will introduce our voicebot integrating text-to-speech (TTS) and speech-to-text (STT) modules provided by FPT.AI. This voicebot can be considered as a critical improvement of a typical ch...

Full description

Main Authors: Tran, D.C., Nguyen, D.L., Hassan, M.F.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.23242 /
Published: Institute of Advanced Engineering and Science 2020
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093884968&doi=10.11591%2feei.v9i6.2620&partnerID=40&md5=b4c80a679ee982969e0615dc06ac2dd9
http://eprints.utp.edu.my/23242/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.23242
recordtype eprints
spelling utp-eprints.232422021-08-19T07:27:23Z Development and testing of an fpt.Ai-based voicebot Tran, D.C. Nguyen, D.L. Hassan, M.F. In recent years, voicebot has become a popular communication tool between humans and machines. In this paper, we will introduce our voicebot integrating text-to-speech (TTS) and speech-to-text (STT) modules provided by FPT.AI. This voicebot can be considered as a critical improvement of a typical chatbot because it can respond to human�s queries by both text and speech. FPT Open Speech, LibriSpeech datasets, and music files were used to test the accuracy and performance of the STT module. For the TTS module, it was tested by using text on news pages in both Vietnamese and English. To test the voicebot, Homestay Service topic questions and off-topic messages were input to the system. The TTS module achieved 100 accuracy in the Vietnamese text test and 72.66 accuracy in the English text test. In the STT module test, the accuracy for FPT open speech dataset (Vietnamese) is 90.51 and for LibriSpeech Dataset (English) is 0 while the accuracy in music files test is 0 for both. The voicebot achieved 100 accuracy in its test. Since the FPT.AI STT and TTS modules were developed to support only Vietnamese for dominating the Vietnam market, it is reasonable that the test with LibriSpeech Dataset resulted in 0 accuracy. © 2020, Institute of Advanced Engineering and Science. All rights reserved. Institute of Advanced Engineering and Science 2020 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093884968&doi=10.11591%2feei.v9i6.2620&partnerID=40&md5=b4c80a679ee982969e0615dc06ac2dd9 Tran, D.C. and Nguyen, D.L. and Hassan, M.F. (2020) Development and testing of an fpt.Ai-based voicebot. Bulletin of Electrical Engineering and Informatics, 9 (6). pp. 2388-2395. http://eprints.utp.edu.my/23242/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description In recent years, voicebot has become a popular communication tool between humans and machines. In this paper, we will introduce our voicebot integrating text-to-speech (TTS) and speech-to-text (STT) modules provided by FPT.AI. This voicebot can be considered as a critical improvement of a typical chatbot because it can respond to human�s queries by both text and speech. FPT Open Speech, LibriSpeech datasets, and music files were used to test the accuracy and performance of the STT module. For the TTS module, it was tested by using text on news pages in both Vietnamese and English. To test the voicebot, Homestay Service topic questions and off-topic messages were input to the system. The TTS module achieved 100 accuracy in the Vietnamese text test and 72.66 accuracy in the English text test. In the STT module test, the accuracy for FPT open speech dataset (Vietnamese) is 90.51 and for LibriSpeech Dataset (English) is 0 while the accuracy in music files test is 0 for both. The voicebot achieved 100 accuracy in its test. Since the FPT.AI STT and TTS modules were developed to support only Vietnamese for dominating the Vietnam market, it is reasonable that the test with LibriSpeech Dataset resulted in 0 accuracy. © 2020, Institute of Advanced Engineering and Science. All rights reserved.
format Article
author Tran, D.C.
Nguyen, D.L.
Hassan, M.F.
spellingShingle Tran, D.C.
Nguyen, D.L.
Hassan, M.F.
Development and testing of an fpt.Ai-based voicebot
author_sort Tran, D.C.
title Development and testing of an fpt.Ai-based voicebot
title_short Development and testing of an fpt.Ai-based voicebot
title_full Development and testing of an fpt.Ai-based voicebot
title_fullStr Development and testing of an fpt.Ai-based voicebot
title_full_unstemmed Development and testing of an fpt.Ai-based voicebot
title_sort development and testing of an fpt.ai-based voicebot
publisher Institute of Advanced Engineering and Science
publishDate 2020
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093884968&doi=10.11591%2feei.v9i6.2620&partnerID=40&md5=b4c80a679ee982969e0615dc06ac2dd9
http://eprints.utp.edu.my/23242/
_version_ 1741196644424089600
score 11.62408

Similar Items