Displaying 1 to 20 from 23 results

DeepLearn - Implementation of research papers on Deep Learning+ NLP+ CV in Python using Keras, Tensorflow and Scikit Learn

  •    Python

Implementation of research papers on Deep Learning+ NLP+ CV in Python using Keras, Tensorflow and Scikit Learn.

awesome-deep-learning-music - List of articles related to deep learning applied to music

  •    TeX

By Yann Bayle (Website, GitHub) from LaBRI (Website, Twitter), Univ. Bordeaux (Website, Twitter), CNRS (Website, Twitter) and SCRIME (Website). The role of this curated list is to gather scientific articles, thesis and reports that use deep learning approaches applied to music. The list is currently under construction but feel free to contribute to the missing fields and to add other resources! To do so, please refer to the How To Contribute section. The resources provided here come from my review of the state-of-the-art for my PhD Thesis for which an article is being written. There are already surveys on deep learning for music generation, speech separation and speaker identification. However, these surveys do not cover music information retrieval tasks that are included in this repository.

Libav - Audio and video processing tools

  •    C

Libav is a collection of libraries and tools to process multimedia content such as audio, video, subtitles and related metadata.




OTTO - Your entire music-making workflow, in one box.

  •    C++

The OTTO is a complete hardware and software solution, with synths, a sampler, effects, sequencers, and studio modules. The interface is modal, easy to use, simple, but most of all, it encourages experimentation. The graphics are quirky, and the workflow is minimal. Yes, the OTTO is heavily inspired by the OP-1, but it is not an OP-1 clone. If you want an OP-1 you can get it here.

Beethoven - :guitar: A maestro of pitch detection.

  •    Swift

Beethoven is an audio processing Swift library that provides an easy-to-use interface to solve an age-old problem of pitch detection of musical signals. You can read more about this subject on Wikipedia. The basic workflow is to get the audio buffer from the input/output source, transform it to a format applicable for processing and apply one of the pitch estimation algorithms to find the fundamental frequency. For the end user it comes down to choosing estimation algorithm and implementation of delegate methods.

arcan - Arcan - [Display Server, Multimedia Framework, Game Engine] -> "Desktop Engine"

  •    C

Arcan is a powerful development framework for creating virtually anything from user interfaces for specialized embedded applications all the way to full-blown standalone desktop environments. At its heart lies a robust and portable multimedia engine, with a well-tested and well-documented Lua scripting interface. The development emphasizes security, debuggability and performance -- guided by a principle of least surprise in terms of API design.


giada - Your Hardcore Loop Machine.

  •    C++

Giada is a free, minimal, hardcore audio tool for DJs, live performers and electronic musicians. How does it work? Just pick up your channel, fill it with samples or MIDI events and start the show by using this tiny piece of software as a loop machine, drum machine, sequencer, live sampler or yet as a plugin/effect host. Giada aims to be a compact and portable virtual device for Linux, Mac OS X and Windows for production use and live sets. Giada is available under the terms of the GNU General Public License. Take a look at the COPYING file for further informations.

LiBLaB

  •    CSharp

LibLab is a C# Library, Networking, Camera, Image Processing, Audio Processing, Video Processing and Computer Vision

beep - A small package that brings sound to any Go program (and real-time audio processing and other casual stuff)

  •    Go

Let's get started! Open an audio file (let's ignore errors for now, never do that in production).Decode the file into a Streamer.

ffmediaelement - WPF MediaElement replacement based on FFmpeg

  •    CSharp

FFME is a close (and I'd like to think better) drop-in replacement for Microsoft's WPF MediaElement Control. While the standard MediaElement uses DirectX (DirectShow) for media playback, FFME uses FFmpeg to read and decode audio and video. This means that for those of you who want to support stuff like HLS playback, or just don't want to go through the hassle of installing codecs on client machines, using FFME might just be the answer.First off, let's review a few concepts. A packet is a group of bytes read from the input. All packets are of a specific MediaType (Audio, Video, Subtitle, Data), and contain some timing information and most importantly compressed data. Packets are sent to a Codec and in turn, the codec produces Frames. Please note that producing 1 frome does not always take exactly 1 packet. A packet may contain many frames but also a frame may require several packets for the decoder to build it. Frames will contain timing informattion and the raw, uncompressed data. Now, you may think you can use frames and show pixels on the screen or data to the sound card. We are close, but we still need to do some additional processing. Turns out different Codecs will produce different uncompressed data formats. For example, some video codecs will output pixel data in ARGB, some others in RGB, and some other in YUV420. Therefore, we will need to Convert these frames into something all hardware can use. I call these converted frames, MediaBlocks. These MediaBlocks will contain uncompressed data in standard Audio and Video formats.

dsp - Digital Signal Processing

  •    Rust

dsp is an early-stage open-source project. It means that API can change at any time. If you think that this library can help you, then let me know. We can discuss future direction and try to stabilize the API. The folder examples contains demo programs which shows how to use this library.

audioworklet-polyfill - 🔊 Polyfill AudioWorklet using the legacy ScriptProcessor API.

  •    Javascript

Polyfills AudioWorklet in browsers that don't support it, using ScriptProcessorNodes under the hood. Worklets are invoked on the main thread within an isolated scope emulating that of a Worklet.

libnyquist - :microphone: Cross platform, C++11 interface to audio decoding

  •    C++

Libnyquist is a small C++11 library for reading sampled audio data from disk or memory. It's ideal to use as an audio asset frontend for games, audio sequencers, music players, and more. The library steers away from patent or GPL license encumbered formats (such as MP3 and AAC). For portability, libnyquist does not link against platform-specific APIs like Windows Media Foundation or CoreAudio, and instead bundles the source code of reference decoders as an implementation detail.

SincNet - SincNet is a neural architecture for efficiently processing raw audio samples.

  •    Python

SincNet is a neural architecture for processing raw audio samples. It is a novel Convolutional Neural Network (CNN) that encourages the first convolutional layer to discover more meaningful filters. SincNet is based on parametrized sinc functions, which implement band-pass filters. In contrast to standard CNNs, that learn all elements of each filter, only low and high cutoff frequencies are directly learned from data with the proposed method. This offers a very compact and efficient way to derive a customized filter bank specifically tuned for the desired application.

dlib - Math, XML, I/O streams, image and audio processing for D

  •    D

dlib is a growing collection of native D language libraries useful for various higher-level projects - such as game engines, rendering pipelines and multimedia applications. It is written in D2 and has no external dependencies aside D's standard library, Phobos. dlib is created and maintained by Timur Gafarov. Important: dlib doesn't support macOS. Please, read the manifesto.