Musical Sound Separation Using Pitch-Based Labeling and Binary Time-Frequency Masking

Monaural musical sound separation attempts to segregate different instrument lines from single-channel polyphonic music. We propose a system that decomposes an input into timefrequency units using an auditory filterbank and utilizes pitch to label which instrument line each time-frequency unit is assigned to. The system is conceptually simple and computationally efficient. Systematic evaluation shows that, despite its simplicity, the proposed system achieves a competitive level of performance.

• Type: Conference
• Year: 2008
• Where: ICASSP
• Authors: Yipeng Li, DeLiang Wang
• Keywords: ICASSP 2008, Instrument Line, Monaural Musical Sound, Signal Processing, Single-channel Polyphonic Music