Название: Computer and Information Science 2021 - Fall
Автор: Roger Lee
Издательство: Springer
Серия: Studies in Computational Intelligence
Год: 2022
Страниц: 160
Язык: английский
Формат: pdf (true)
Размер: 17.3 MB

This edited book presents scientific results of the 21th IEEE/ACIS International Fall Virtual Conference on Computer and Information Science (ICIS 2021-Fall) held on October 13-15, 2021, in Xi’an China. The aim of this conference was to bring together researchers and scientists, businessmen and entrepreneurs, teachers, engineers, computer users, and students to discuss the numerous fields of computer science and to share their experiences and exchange new ideas and information in a meaningful way. Research results about all aspects (theory, applications, and tools) of computer and information science and to discuss the practical challenges encountered along the way and the solutions adopted to solve them.

The conference organizers selected the best papers from those papers accepted for presentation at the conference. The papers were chosen based on review scores submitted by members of the program committee and underwent further rigorous rounds of review. From this second round of review, 13 of the conference’s most promising papers are then published in this Springer (SCI) book and not the conference proceedings. We impatiently await the important contributions that we know these authors will bring to the field of computer and information science.

With the boom of Artificial Intelligence technology, numerous research directions like speech recognition, image recognition, and data mining, are going through a period of rapid and revolutionary development. As a result, in the area of speech recognition, technology giants like Google, Apple and Microsoft had already developed robust speech recognition engines for billions of daily active users.

However, issues related to privacy, security, and even politics led by technological barriers will undoubtedly turn into a significant disadvantage for the stability of local speech recognition services. Admittedly, these tech giants are providing some API for custom software development, but the core technology is still confidential and cannot be accessed locally. Not only the service providers could cause these potential problems, but also local users are raising high demand for speech recognition functions. That is why it is important to achieve a localized speech recognition engine. Currently, there are several platforms for speech recognition development, such as TensorFlow, Kaldi and HTK. For this project, comparison needs to be made within these development tools. Explicitly, for test purpose, all tools will produce a model using the same dataset. The most efficient and convenient platform will be the most suitable to work on.