Revisiting Singing Voice Detection: a Quantitative Review and the Future Outlook
This work addresses the need for more robust singing voice detection in music information retrieval, but it is incremental as it builds on existing methods without introducing a new paradigm.
The authors tackled the problem of improving robustness in singing voice detection systems by conducting an error analysis on three recent systems and testing them on new curated and generated datasets to identify pitfalls not revealed by existing data.
Since the vocal component plays a crucial role in popular music, singing voice detection has been an active research topic in music information retrieval. Although several proposed algorithms have shown high performances, we argue that there still is a room to improve to build a more robust singing voice detection system. In order to identify the area of improvement, we first perform an error analysis on three recent singing voice detection systems. Based on the analysis, we design novel methods to test the systems on multiple sets of internally curated and generated data to further examine the pitfalls, which are not clearly revealed with the current datasets. From the experiment results, we also propose several directions towards building a more robust singing voice detector.