User Tools
singing_separation
====== Differences ====== This shows you the differences between two versions of the page.
|
singing_separation [2013/06/30 17:20] personhuang |
singing_separation [2013/06/30 17:32] (current) personhuang |
||
|---|---|---|---|
| Line 18: | Line 18: | ||
| ==== - HAMR-RPCA ==== | ==== - HAMR-RPCA ==== | ||
| **Objective**\\ | **Objective**\\ | ||
| - | minimize $||A||_* + \lambda ||E||_1 + \gamma || E - E_0 ||_F ^2$ subject to $A+E = M$\\ | + | - Minimize $||A||_* + \lambda ||E||_1 + \gamma || E - E_0 ||_F ^2$ subject to $A+E = M$\\ |
| **Framework**\\ - Given mixed signals, run RPCA to obtain $E_{RPCA}$. \\ - We use dynamic time warping to warp spoken lyrics $E_{spoken}$ to $E_{RPCA}$. Define $E_0$ as the $E_{spoken}$ for HAMR-RPCA. | **Framework**\\ - Given mixed signals, run RPCA to obtain $E_{RPCA}$. \\ - We use dynamic time warping to warp spoken lyrics $E_{spoken}$ to $E_{RPCA}$. Define $E_0$ as the $E_{spoken}$ for HAMR-RPCA. | ||
| Line 27: | Line 27: | ||
| ==== - HAMR-NMF - Separation with codebook ==== | ==== - HAMR-NMF - Separation with codebook ==== | ||
| - | **Idea**\\ Separate the singing and background with the help of the dictionary that was learnt from the speech | + | **Idea**\\ - Separate the singing and background with the help of the dictionary that was learnt from the speech |
| - | **Intuition**\\ Because the lyric is assumed to be known in our cases, the hope of this model is that the dictionary learnt from the spoken lyrics can encode the information which is the same in the singing voice. | + | **Intuition**\\ - Because the lyric is assumed to be known in our cases, the hope of this model is that the dictionary learnt from the spoken lyrics can encode the information which is the same in the singing voice. |
| **Problems**\\ - Pitch difference\\ - Voice difference | **Problems**\\ - Pitch difference\\ - Voice difference | ||
| Line 35: | Line 35: | ||
| **Solutions**\\ - Generate extra dictionary elements.\\ - Adaptation | **Solutions**\\ - Generate extra dictionary elements.\\ - Adaptation | ||
| - | So, the overall formulation: | + | **Objectives**\\ - $\min_{H,A}\lambda||H||_1+\beta||A||_*+||W-W_0||_2^2$ subject to $Y=WH+A$ |
| - | $\min_{H,A}\lambda||H||_1+\beta||A||_*+||W-W_0||_2^2$ subject to $Y=WH+A$ | + | |
| - | Whole process steps:\\ - Synthesize the lyric to speech\\ - Extracted the dictionary from the synthesized speech\\ - Generate extra dictionary elements\\ - Running the system | + | **Whole process steps**\\ - Synthesize the lyric to speech\\ - Extracted the dictionary from the synthesized speech\\ - Generate extra dictionary elements\\ - Running the system |
| **Result** | **Result** | ||
singing_separation.1372627217.txt.gz · Last modified: 2013/06/30 17:20 by personhuang
Page Tools
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 3.0 Unported
