Genre-conditioned Acoustic Models for Automatic Lyrics Transcription of Polyphonic Music
This work addresses the problem of accurate lyrics transcription for music listeners and researchers, but it is incremental as it builds on pre-trained models with lightweight adapters.
The paper tackles the challenge of automatic lyrics transcription in polyphonic music by proposing a genre-conditioned network that adapts to different music genres like pop and metal, resulting in improved performance over existing systems.
Lyrics transcription of polyphonic music is challenging not only because the singing vocals are corrupted by the background music, but also because the background music and the singing style vary across music genres, such as pop, metal, and hip hop, which affects lyrics intelligibility of the song in different ways. In this work, we propose to transcribe the lyrics of polyphonic music using a novel genre-conditioned network. The proposed network adopts pre-trained model parameters, and incorporates the genre adapters between layers to capture different genre peculiarities for lyrics-genre pairs, thereby only requiring lightweight genre-specific parameters for training. Our experiments show that the proposed genre-conditioned network outperforms the existing lyrics transcription systems.