Speech Separation from Background of Music Based on Single-channel Recording
Xuecheng Jin, Zengfu Wang · 2006
This paper presents a speech separation algorithm, which is capable of extracting speech signals from music background when given only a single-channel recording. The main idea is to employ both the tool of spectrogram and the image processing methods to solve the problem of speech signals processing. Edge detection algorithm and Hough transform are used to detect the fundamental frequency and the corresponding harmonic components of the music. The experimental results show that the proposed algorithm can effectively remove background music from the input signals and output the speech signals needed.