Audeo: Audio Generation for a Silent Performance Video

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.

arXiv commentPlease see associated video at https://www.youtube.com/watch?v=8rS3VgjG7_c

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• WaveNet: A Generative Model for Raw Audio
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Tacotron: Towards End-to-End Speech Synthesis
• Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
• Onsets and Frames: Dual-Objective Piano Transcription
• Virtual Piano using Computer Vision

Cited by in corpus (7)

• Video Background Music Generation with Controllable Music Transformer
• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
• Multi-Instrumentalist Net: Unsupervised Generation of Music from Body Movements
• Soundify: Matching Sound Effects to Video
• Foley Music: Learning to Generate Music from Videos
• The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos
• EMID: An Emotional Aligned Dataset in Audio-Visual Modality