3 citations · 10 across the 10 of their papers we have counts for
10 papers
Diff-MST: Differentiable Mixing Style Transfer
Soumya Sai Vanka, Christian Steinmetz, Jean-Baptiste Rolland +2
Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for…
SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache +3
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality. One of the most time-con…
High-Fidelity Noise Reduction with Differentiable Signal Processing
Christian J. Steinmetz, Thomas Walther, Joshua D. Reiss
Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly pe…
Optimization Techniques for a Physical Model of Human Vocalisation
Mateo Cámara, Zhiyuan Xu, Yisu Zong +2
We present a non-supervised approach to optimize and evaluate the synthesis of non-speech audio effects from a speech production model. We use the Pink Trombone synthesizer as a ca…
General Purpose Audio Effect Removal
Matthew Rice, Christian J. Steinmetz, George Fazekas +1
Although the design and application of audio effects is well understood, the inverse problem of removing these effects is significantly more challenging and far less studied. Recen…
Modulation Extraction for LFO-driven Audio Effects
Christopher Mitcheltree, Christian J. Steinmetz, Marco Comunità +1
Low frequency oscillator (LFO) driven audio effects such as phaser, flanger, and chorus, modify an input signal using time-varying filters and delays, resulting in characteristic s…