Paper Title: "Real-Time Singing Performance Improvement through Pitch Correction using Apache Kafka Stream Processing"
Student: Bui Anh Khoi – 19520649 – Majoring in Software Engineering, Class of 2019
Supervisor: Dr. Do Trong Hop
Abstract:
Singing, an essential art form in our spiritual lives, often requires precise control over pitch accuracy to convey emotions effectively. However, the challenge of maintaining pitch accuracy often leads to compromised performance quality, with "out of tune" issues being a significant problem in this field. This study introduces a system designed to correct raw vocal pitch while preserving the original vocal characteristics. Utilizing the Time-Domain Pitch-Synchronous Overlap and Add (TD-PSOLA) method on notes extracted through the time-domain pYin technique, the system corrects pitches without altering the singer's unique vocal qualities. Additionally, the system employs Kafka's Data Streaming architecture to address the challenges posed by big data.
"I would like to express my sincere gratitude to Dr. Do Trong Hop, who has consistently provided robust support, advice, and guidance throughout my studies and the completion of this research."
The ICIT2023 conference is an International Conference on the Intelligence of Things sponsored by Springer. This conference focuses on the latest technologies, applications, and research in the field of the Internet of Things (IoT), Artificial Intelligence of Things (AIoT), and related areas in Information Technology. Accepted papers presented at the conference will be published by Springer in the Lecture Notes on Data Engineering and Communications Technologies series, indexed by SCOPUS (Q3).
Detailed Information: https://www.facebook.com/UIT.Fanpage/posts/pfbid0Dehf6Qyew25dhYh5JbmfLZFpzezNRbTFFwa8SDZsLb3ttUuJywcQz5xDwDQEcMwXl
Hai Bang - Communication Collaborator, University of Information Technology
English version: Phan Huy Hoang
