filipemlins Goto Github PK

automatic-music-transcription-harmonica

This paper presents a method for automatic transcription of the diatonic Harmonica instrument. It estimates the multi-pitch activations through a spectrogram factorisation framework. This framework is based on Probabilistic Latent Content Analysis (PLCA) and uses a fixed 4-dimensional tensor with spectral templates extracted from Harmonica’s instrument timbre. Methods based on spectrogram factorisation may suffer from local-optima issues in the presence of harmonic overlapping or considerable timbre variability. To alleviate this issue, we propose a set of harmonic constraints that are inherent to the Harmonica instrument note layout or are caused by specific diatonic Harmonica playing techniques. These constraints help to guide the factorisation process until the convergence into meaningful multi-pitch activations is achieved. This work also builds a new audio dataset containing solo recordings of diatonic Harmonica excerpts and the respective multi-pitch annotations. We compare our proposed approach against multiple baseline techniques for automatic music transcription on this dataset and report the evaluation based on frame-based F-measure statistics.

dataset

deliverooreactnative

React native project with sanity and other technologies

faucet

Blockchain Solidity Course

filipemlins.github.io

firebaseuiandroiddemo

FirebaseUI Android demo application.

harmonica-dataset

Diatonic Harmonica Dataset

hls4ml

Machine learning in FPGAs using HLS

iamhere-app

i am here - app expo react native

instrumentclassifier

Instrument Classifier using CNN and RNN.

juceaudiodemo

Demo project for implementing JUCE in an Android and iOS app

jucyfluttering

A simple iOS &Android example for how to integrate Flutter (Dart) as user interface and JUCE (C++) as backend.

musicfactoryapps.github.io

nas-hls4ml

nas hls4ml NNs music and audio applications

nas_hls4ml

NAS hls4ml for music and audio NNs

nativeandroidjucesamplefirebase

neural-network-high-level-synthesis-lenet

Neural Network Lenet 5 - High Level Synthesis with Neural Net generated in python generating the weights files, a simple test which we can compare the intermediate outputs, and generate 10k sample test to be simulated in HLS. Also, in the HLS project we have a test bench which evaluate the HLS neural network with 10k samples and returns the accuracy.

react-native-practical-guide-code

Course code & attachments for our "React Native - The Practical Guide" (https://acad.link/react-native) course.

react-native-template-obytes

📱 A template for your next React Native project 🚀, Made with developer experience and performance first: Expo,TypeScript,TailwindCSS, Husky, Lint-Staged, react-navigation, react-query, react-hook-form.

register-file-criticality-on-embedded-microprocessor-reliability

We investigate the criticality of register file and compiler optimization on ARM-based SoCs reliability. The analysis performed using a homemade interruption-based efficient fault injector is correlated with heavy ions experiment results.

rn-pratical-guide

React Native Pratical Guide Course

rocket-discover-dev-links

salvandopets

turntable

DIY heavy duty and high precision turntable for 3D Scanning

wle-networking

Basic networking components for Wonderland Engine based off of peer.js

wonderland-engine-multiplayer