| Autor: |
Snehal R. Kharvatkar, D. G. Khairnar, Indraneel C. Naik, Manish Sharma |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA). |
| DOI: |
10.1109/iccubea.2018.8697523 |
| Popis: |
The pitch detection is an integral element of automatic music transcription system. Empirical Mode Decomposition (EMD) technique plays a key part in the pitch detection. With this technique, any complicated data set comprising of frequency-amplitude points can be decomposed into small number of finite Intrinsic Mode Functions (IMF). The IMF logic is in accordance with a well-behaved and well proven Hilbert transform. In this paper, a step by step algorithm for detecting pitch period from classical music signal based on Hilbert-Huang transform (HHT) is proposed. Traditional windowing methods have two limitations namely overlapping of windows and an assumption of stationary pitch period within a window. In contrast, HHT shows no limitations on window selection and allows pitch period changing within windows. It also can be used to monitor the variation of the pitch. To validate the proposed method, the pure tone of standard pitch is used. The results show that the variation of the pitch period can be accurately detected. This demonstrates the successful application of Hilbert-Huang transform for pitch detection from Indian classical music signal. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
