On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Improvisation”

Query-based Deep Improvisationcs.SD

Generative model blends query input with latent states for structured improvisation.

problem Generating structured music from latent states of a neural network.

method Used a Variational Autoencoder (VAE) trained on a specific style corpus, and controlled blending with a noisy channel.

result Generated music with longer-term structure that blends query input with network style.

deep learning music generation variational autoencoder improvisation latent states

2019-06-21abs ↗pdf ↗

Piano Geniecs.LG

Piano Genie lets non-musicians improvise on a piano.

problem Improvising on the piano for non-musicians.

method Trained recurrent neural network autoencoders with discrete bottlenecks to learn mappings between user inputs and piano pieces.

result Piano Genie allows users to improvise on the piano with musically meaningful constraints.

Piano Improvisation Neural Networks Autoencoders Recurrent

2018-10-11abs ↗pdf ↗

Incorporating prior knowledge about structural constraints in model identificationcs.LG

Proposes SPCA to incorporate structural constraints in model identification.

problem Model identification with partial structural knowledge.

method Structural Principal Component Analysis (SPCA) that leverages structural information.

result Demonstrates improved model estimates using synthetic and industrial data.

model identification structural constraints principal component analysis chemical industries

2020-07-08abs ↗pdf ↗

Deep Autotuner: a Pitch Correcting Network for Singing Performancescs.SD

Deep Autotuner corrects singing pitch using neural networks.

problem Automatic pitch correction for singing performances.

method Neural network model trained on spectrograms of singing and accompaniment.

result Neural network predicts continuous pitch shifts, allowing for improvisation and harmonization.

pitch correction singing performance neural networks spectrograms continuous value

2020-02-12abs ↗pdf ↗

An automated approach for task evaluation using EEG signalscs.LG

Automated EEG analysis gauges mental workload in task evaluation.

problem Evaluating mental workload in user tasks, especially complex ones.

method Experimental setup, EEG data analysis, feature extraction, machine learning.

result Machine learning outperforms traditional methods in mental workload estimation.

EEG mental workload task evaluation machine learning workload assessment

2019-11-07abs ↗pdf ↗