Marius Miron's repositories
pydata2017bcn
Convolutional neural networks for audio processing: starting pack
Note-refinement-
Audio-to-score alignment at the note level
beatStation
beatStation - an openFrameworks tapping recorder interface
beatStationLinux
the tapping recording station adapted for Linux
conference-archive
Machinery for archiving conference proceedings and maintaining metadata.
DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
facescrub_subset
create a subset of the facescrub cropped dataset containing a given number of people
feeling-responsive
»Feeling Responsive« is a free flexible theme for Jekyll built on Foundation framework. You can use it for your company site, as a portfolio or as a blog.
LibriMix
An open source dataset for source separation
mir-datasets
Simple collection of MIR datasets with metadata and links
mirdata
common loaders for mir datasets
MixCycle
This repository contains the audio samples and the source code that accompany the paper: "MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training"
notmnist_convert
notmnist small dataset resized to 32x32,converted to numpy array, and pickled
paper_templates
Repository for paper templates in ISMIR Proceedings
proceedings-builder
Tools for generating full ISMIR proceedings (HTML + PDF)
sherlocksound
googlemaps/freesound game
tfrecord
TFRecord reader for PyTorch
unsup_speech_enh_adaptation
Unsupervised domain adaptation for conversational speech enhancement using RemixIT
webMUSHRA_jp
a MUSHRA compliant web audio API based experiment software