@inproceedings{7ccb804b5ef54849aafb5abf5eb7ae0e,
title = "A Method to Real-Time Update Speaker Pronunciation Time-Database for the Application of Informatized Caption Enhancement by IBM Watson API",
abstract = "One of the major AI research fields is natural language processing by speech recognition. IBM Watson is one of the representative tools for this speech recognition system which can automatically generate not only the recognized words from voice signal but also the speaker ID and timing information of each words including the starting time and the ending time. However, IBM Watson is not enough good and easily generate incorrect recognition output when there are some noise in the audio signal, especially for movies where background music and special sound effects are incorporated together. There were some studies to solve this problem using the IBM Watson API based on the assumption that speaker pronunciation time DB was already implemented properly. But, it is not easy to make speaker pronunciation time DB and it requires big cost. In this paper, to resolve this problem of speaker pronunciation time DB, we introduce an efficient method to implement and update the speaker pronunciation time DB in real time.",
keywords = "IBM Watson API, Informatized caption, Speaker pronunciation time-DB, Speech recognition",
author = "Choi, {Yong Sik} and Kim, {In Hwan} and Yang, {Hyun Mo} and Lim, {Dong Woo} and Ailing Lin and Jung, {Jin Woo}",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Singapore Pte Ltd.; 6th International Conference on Frontier Computing, FC 2018 ; Conference date: 03-07-2018 Through 06-07-2018",
year = "2019",
doi = "10.1007/978-981-13-3648-5_56",
language = "English",
isbn = "9789811336478",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "490--495",
editor = "Lin Hui and Hung, {Jason C.} and Yen, {Neil Y.}",
booktitle = "Frontier Computing - Theory, Technologies and Applications FC 2018",
address = "Germany",
}