Timbre Space Learning for Augmentation of Musical Audio Synthesizer Interfaces

2021 ◽  
Author(s):  
Jeff Gregorio
Keyword(s):  
Musical Audio

scholarly journals Stochastic Restoration of Heavily Compressed Musical Audio Using Generative Adversarial Networks

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1349
Author(s):  
Stefan Lattner ◽  
Javier Nistal
Keyword(s):  
Data Storage ◽  
Audio Signal ◽  
Human Perception ◽  
Generative Adversarial Networks ◽  
Audio Signals ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Extensive Evaluation ◽  
Listening Tests ◽  
Musical Audio

Lossy audio codecs compress (and decompress) digital audio streams by removing information that tends to be inaudible in human perception. Under high compression rates, such codecs may introduce a variety of impairments in the audio signal. Many works have tackled the problem of audio enhancement and compression artifact removal using deep-learning techniques. However, only a few works tackle the restoration of heavily compressed audio signals in the musical domain. In such a scenario, there is no unique solution for the restoration of the original signal. Therefore, in this study, we test a stochastic generator of a Generative Adversarial Network (GAN) architecture for this task. Such a stochastic generator, conditioned on highly compressed musical audio signals, could one day generate outputs indistinguishable from high-quality releases. Therefore, the present study may yield insights into more efficient musical data storage and transmission. We train stochastic and deterministic generators on MP3-compressed audio signals with 16, 32, and 64 kbit/s. We perform an extensive evaluation of the different experiments utilizing objective metrics and listening tests. We find that the models can improve the quality of the audio signals over the MP3 versions for 16 and 32 kbit/s and that the stochastic generators are capable of generating outputs that are closer to the original signals than those of the deterministic generators.

On the Relations Between Audio Features and Room Acoustic Parameters of Auralizations

2013 ◽  
Vol 135 (6) ◽  
Author(s):  
Salvador Cerdá ◽  
Alicia Giménez ◽  
Radha Montell ◽  
Arturo Barba ◽  
Radu Lacatis ◽  
...  
Keyword(s):  
Room Acoustics ◽  
Subjective Perception ◽  
Audio Signals ◽  
Acoustic Parameters ◽  
Acoustic Characteristics ◽  
Statistical Correlations ◽  
Audio Features ◽  
Musical Characteristics ◽  
Audio Files ◽  
Musical Audio

The usual parameters in room acoustics are used to quantify the acoustic characteristics of rooms and their relation to the subjective perception of transmitted signals. Audio features (calculated with MIRToolbox) have been designed to study the relationships between the characteristics of musical audio files and their subjective perception. Both musical characteristics and acoustic parameters are oriented towards acoustic perception. By using auralizations with calibrated models of auditoriums and tools from the MIRtoolbox it is possible to jointly work with the calculation of audio features and room parameters. In this work, the statistical correlations between C80, STI, D50, EDT, RT and certain audio features have been analyzed. The Pearson r values are higher than 0.8 in all cases. These high correlations enable acoustic parameters to be calculated from the musical characteristics of auralized audio signals.

Sparse Linear Regression With Structured Priors and Application to Denoising of Musical Audio

2008 ◽  
Vol 16 (1) ◽  
pp. 174-185 ◽  
Author(s):  
CÉdric Fevotte ◽  
Bruno Torresani ◽  
Laurent Daudet ◽  
Simon J. Godsill
Keyword(s):  
Linear Regression ◽  
Musical Audio

Profiling musical audio processing effects with deep neural networks

2018 ◽  
Vol 144 (3) ◽  
pp. 1753-1753
Author(s):  
Scott H. Hawley ◽  
Benjamin L. Colburn ◽  
Stylianos I. Mimilakis
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Audio Processing ◽  
Processing Effects ◽  
Musical Audio
Sign in / Sign up

Export Citation Format

Share Document