1 citations · 1 across the 5 of their papers we have counts for
5 papers · 1 filter
Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation
Keren Shao, Ayaka Kawano, Shlomo Dubnov
We ask: given a retrieved source audio and a separate reference audio , can we synthesize novel audio out of this pair such that remains acoustically consist…
kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization
Keren Shao, Ke Chen, Matthew Baas +1
Robustness is critical in zero-shot singing voice conversion (SVC). This paper introduces two novel methods to strengthen the robustness of the kNN-VC framework for SVC. First, kNN…
Interpreting Graphic Notation with MusicLDM: An AI Improvisation of Cornelius Cardew's Treatise
Tornike Karchkhadze, Keren Shao, Shlomo Dubnov
This work presents a novel method for composing and improvising music inspired by Cornelius Cardew's Treatise, using AI to bridge graphic notation and musical expression. By levera…
Music Enhancement with Deep Filters: A Technical Report for The ICASSP 2024 Cadenza Challenge
Keren Shao, Ke Chen, Shlomo Dubnov
In this challenge, we disentangle the deep filters from the original DeepfilterNet and incorporate them into our Spec-UNet-based network to further improve a hybrid Demucs (hdemucs…
Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction
Keren Shao, Ke Chen, Taylor Berg-Kirkpatrick +1
In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modific…