Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations
This addresses the need for precise accompaniment generation in music creation, though it appears incremental as it builds on existing deep learning approaches.
The paper tackled the problem of generating accompaniments for singing by proposing a text-controllable method, resulting in successful generation of 10-second accompaniments aligned with vocal input and text prompts.
Singing is one of the most cherished forms of human entertainment. However, creating a beautiful song requires an accompaniment that complements the vocals and aligns well with the song instruments and genre. With advancements in deep learning, previous research has focused on generating suitable accompaniments but often lacks precise alignment with the desired instrumentation and genre. To address this, we propose a straightforward method that enables control over the accompaniment through text prompts, allowing the generation of music that complements the vocals and aligns with the song instrumental and genre requirements. Through extensive experiments, we successfully generate 10-second accompaniments using vocal input and text control.