Singing Voice Separation and Pitch Extraction from Monaural Polyphonic Audio Music via DNN and Adaptive Pitch Tracking

With the explosive growth of audio music everywhere over the Internet, it is becoming more important to be able to classify or retrieve audio music based on their key components, such as vocal pitch for common popular music. This paper proposes a novel and effective two-stage approach to singing pitch extraction, which involves singing voice separation and pitch tracking for monaural polyphonic audio music. The first stage extracts singing voice from the songs by using deep neural networks in a supervised setting. Then the second stage estimates the pitch based on the extracted singing voice in a robust manner. Experimental results based on MIR-1K showed that the proposed approach outperforms a previous state-of-the-art approach in raw-pitch accuracy. Moreover, the proposed approach has been submitted to the singing voice separation and audio melody extraction tasks of Music Information Retrieval Evaluation eXchange (MIREX) in 2015. The results of the competition shows that the proposed approach is superior to other submitted algorithms, which demonstrates the feasibility of the method for further applications in music processing.