From the 3 of 10 linked papers with an AI index.
10 papers
From Prediction to Collaboration: Interactive Symbolic Music Analysis
Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth +1
The paper introduces an interactive framework for symbolic Roman‑numeral music analysis that combines strong predictive models with support for constrained completion, revision, an…
Low-Latency Neural Models for Real-Time Music Enhancement
Emmanouil Karystinaios, Jonathan Greif, David Nadrchal +2
The paper benchmarks compact causal neural networks for real-time music enhancement, analyzing their performance under low‑latency constraints and various degradation types.
Neural Morphing: Sequence-Optimized Token-Level Morphing in Neural Audio Codecs
Emmanouil Karystinaios
The paper introduces Neural Morphing, a training‑free technique that edits audio by selecting and replacing residual‑vector‑quantized token grains from a pretrained neural audio co…
Dilemmadata: On the Interoperability of Heterogeneous Roman Numeral Datasets
Johannes Hentschel, Emmanouil Karystinaios, Gerhard Widmer +1
In recent years, there has been growing effort to annotate and collect large-scale corpora of Roman numeral analyses in support of data-driven studies in tonal harmony. We introduc…
Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN
Tobias Morocutti, Emmanouil Karystinaios, Jonathan Greif +1
Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts v…
How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation
Deepak Kumar, Emmanouil Karystinaios, Gerhard Widmer +1
Music often shares notable parallels with language, motivating the use of pretrained large language models (LLMs) for symbolic music understanding and generation. Despite growing i…