MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion
Abstract
We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel deep learning-based pitch estimation model that accurately estimates pitch trajectory in noisy and reverberant acoustic environments. Our model leverages the periodic characteristics of audio signals and involves two key steps: extracting pitch periodicity using periodic non-periodic convolution (PNP-Conv) blocks and estimating pitch by aggregating multi-level features using a modified bi-directional feature pyramid network (BiFPN). We evaluate our model on speech and music datasets and achieve superior pitch estimation performance compared to state-of-the-art baselines while using fewer model parameters. Our model achieves 99.20 % accuracy in pitch estimation on a clean musical dataset. Overall, our proposed model provides a promising solution for accurate pitch estimation in challenging acoustic environments and has potential applications in audio signal processing.
Keywords
Cite
@article{arxiv.2306.09640,
title = {MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion},
author = {Woo-Jin Chung and Doyeon Kim and Soo-Whan Chung and Hong-Goo Kang},
journal= {arXiv preprint arXiv:2306.09640},
year = {2025}
}
Comments
Accepted at INTERSPEECH 2023 Code could be found in https://github.com/Woo-jin-Chung/MF-PAM_mfpam_pitch_estimation_pytorch