Audeo: Audio Generation for a Silent Performance Video

TL;DR

Audeo is a system that converts silent piano performance videos into plausible, high-quality music by translating visual cues into symbolic representations and synthesizing audio, demonstrating the feasibility of visual-to-audio transformation.

Contribution

This work introduces a complete pipeline for generating music from silent performance videos, combining visual-to-symbolic translation and audio synthesis, which was not previously demonstrated.

Findings

Generated music has reasonable audio quality.

Music can be recognized with high precision by music identification software.

The system works effectively on 'in the wild' videos.

Abstract

We present a novel system that gets as an input video frames of a musician playing the piano and generates the music for that video. Generation of music from visual cues is a challenging problem and it is not clear whether it is an attainable goal at all. Our main aim in this work is to explore the plausibility of such a transformation and to identify cues and components able to carry the association of sounds with visual events. To achieve the transformation we built a full pipeline named `\textit{Audeo}' containing three components. We first translate the video frames of the keyboard and the musician hand movements into raw mechanical musical symbolic representation Piano-Roll (Roll) for each video frame which represents the keys pressed at each time step. We then adapt the Roll to be amenable for audio synthesis by including temporal correlations. This step turns out to be critical for meaningful audio generation. As a last step, we implement Midi synthesizers to generate realistic music. \textit{Audeo} converts video to audio smoothly and clearly with only a few setup constraints. We evaluate \textit{Audeo} on `in the wild' piano performance videos and obtain that their generated music is of reasonable audio quality and can be successfully recognized with high precision by popular music identification software.