Layered Nonnegative Matrix Factorization for Speech Separation
檔案
本條目沒有附加檔案。
日期
2015
類型
系所
期刊名稱
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5
卷期與頁次
頁 628–632
ISBN
978-1-5108-1790-6
語言
英文
摘要
This paper proposes a layered nonnegative matrix factorization (L-NMF) algorithm for speech separation. The standard NMF method extracts parts-based bases out of nonnegative training data and is often used to separate mixed spectrograms. The proposed L-NMF algorithm comprises of several layers of standard NMF blocks. During training, each layer of the L-NMF is initialized separately and then fine-tuned by minimizing the propagated reconstruction error. More complicated bases of the training data are emerged in deeper layers of the L-NMF by progressively combining parts-based bases extracted in the first layer. In other words, these complicated bases contain collective information of the parts-based bases. The bases deciphered by all layers are then used to separate spectrograms in the conventional NMF way. Simulation results show the proposed L-NMF outperforms the standard NMF in terms of the source-to-distortion ratio (SDR).
所屬典藏
會議論文引用此條目
Hsu, C.-C., Chien, J.-T., & Chi, T.-S. (2015). Layered Nonnegative Matrix Factorization for Speech Separation. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 628–632. https://ir.lib.nycu.edu.tw/handle/11536/136224
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/11536/136224