CNN BASED TWO-STAGE MULTI-RESOLUTION END-TO-END MODEL FOR SINGING MELODY EXTRACTION
檔案
本條目沒有附加檔案。
日期
2019-01-01
類型
系所
期刊名稱
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
卷期與頁次
頁 1005–1009
ISSN
1520-6149
ISBN
978-1-4799-8131-1
語言
英文
摘要
Inspired by human hearing perception, we propose a two-stage multi-resolution end-to-end model for singing melody extraction in this paper. The convolutional neural network (CNN) is the core of the proposed model to generate multi-resolution representations. The 1-D and 2-D multi-resolution analysis on waveform and spectrogram-like graph are successively carried out by using 1-D and 2-D CNN kernels of different lengths and sizes. The 1-D CNNs with kernels of different lengths produce multi-resolution spectrogram-like graphs without suffering from the trade-off between spectral and temporal resolutions. The 2-D CNNs with kernels of different sizes extract features from spectro-temporal envelopes of different scales. Experiment results show the proposed model outperforms three compared systems in three out of five public databases.
關鍵詞
Melody extractionmulti-resolutionconvolution neural networkend-to-end learningmusic information retrieval所屬典藏
會議論文引用此條目
Chen, M.-T., Li, B.-J., & Chi, T.-S. (2019). CNN BASED TWO-STAGE MULTI-RESOLUTION END-TO-END MODEL FOR SINGING MELODY EXTRACTION. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 1005–1009. https://ir.lib.nycu.edu.tw/handle/11536/152923
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152923