用卷积神经网络从频谱图直接估测音高，准确率超92%。
Real-Time Pitch/F0 Detection Using Spectrogram Images and Convolutional Neural Networks
- 将频谱图转为图像，用CNN直接预测音高轮廓
- 92%的预测结果与真实音高相关性较强或中等
- 在不同信噪比下比现有方法提升约5%检测率
本文提出一种新方法，通过卷积神经网络和图像处理技术，直接从频谱图估计基频（F0）。该方法表现出优异的检测精度：92%的预测音高轮廓与真实音高轮廓具有强或中等相关性。实验对比显示，在不同信噪比条件下，该方法相比其他先进CNN方法，检测率提升约5%。
原文摘要 · Abstract (English)
This paper presents a novel approach to detect F0 through Convolutional Neural Networks and image processing techniques to directly estimate pitch from spectrogram images. Our new approach demonstrates a very good detection accuracy; a total of 92% of predicted pitch contours have strong or moderate correlations to the true pitch contours. Furthermore, the experimental comparison between our new approach and other state-of-the-art CNN methods reveals that our approach can enhance the detection rate by approximately 5% across various Signal-to-Noise Ratio conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。