Exploring Aligned Lyrics-Informed Singing Voice Separation
This work addresses the problem of separating singing voices from music for audio processing applications, but it is incremental as it builds on existing separation networks with added lyrics information.
The paper tackles singing voice separation by incorporating aligned lyrics as additional input, resulting in improved performance compared to models without this information. Experiments confirm that the performance gain is due to phonetic content in the lyrics, not just vocal activity cues.
In this paper, we propose a method of utilizing aligned lyrics as additional information to improve the performance of singing voice separation. We have combined the highway network-based lyrics encoder into Open-unmix separation network and show that the model trained with the aligned lyrics indeed results in a better performance than the model that was not informed. The question now remains whether the increase of performance is actually due to the phonetic contents that lie in the informed aligned lyrics or not. To this end, we investigated the source of performance increase in multifaceted ways by observing the change of performance when incorrect lyrics were given to the model. Experiment results show that the model can use not only just vocal activity information but also the phonetic contents from the aligned lyrics.