• Corpus ID: 58040905

Piper: Audio Feature Extraction in Browser and Mobile Applications

  title={Piper: Audio Feature Extraction in Browser and Mobile Applications},
  author={Lucas Thompson and Chris Cannam and Mark B. Sandler},
Piper is a protocol for audio analysis and feature extraction. We propose a data schema and API that can be used to support both remote audio feature extraction services and feature extractors loaded directly into a host application. We provide a means of using existing audio feature extractor implementations with this protocol. In this talk we demonstrate several use-cases for Piper, including an“audio notebook”mobile application using Piper modules to analyse recordings; a web service for… 

Figures from this paper

A javascript musical machine listening library.
More advanced interactive web browser based computer music applications are supported through a new javascript library for musical machine listening, MMLL. The library includes such facilities as
A User-Adaptive Automated DJ Web App with Object-Based Audio and Crowd-Sourced Decision Trees
The concepts behind a web-based minimal-UI DJ system that adapts to the user’s preference via simple interactive decisions and feedback on taste are described and different types of transitions can be modeled using simple musical constraints are shown.
Internet of Musical Things: Vision and Challenges
This paper presents a vision in which the IoMusT enables the connection of digital and physical domains by means of appropriate information and communication technologies, fostering novel musical applications and services and identifies key capabilities missing from today's systems.
Audio and Music Analysis on the Web using Essentia.js
This work wrote the API using TypeScript for static typing, and to be able to transpile the library for new and old JS targets (for forward and backward compatibility) as the ECMAScript (ES)14 specification continues to evolve.


Meyda: an Audio Feature Extraction Library for the Web Audio API
Myda provides the first library for audio feature extraction in the web client, which will enable music information retrieval systems, complex visualisations and a wide variety of technologies and creative projects that previously were relegated to native software.
JS-Xtract: A Realtime Audio Feature Extraction Library for the Web
JS-Xtract is an efficient modular JavaScript library for audio feature extraction, capable of operating on arbitrary time-series data, or being bound to Web Audio objects. The library implements an
WAAX: Web Audio API eXtension
Common issues in web audio programming are described, how WAAX can speed up the development is illustrated, and future developments are discussed.
Web Audio Modules
This paper proposes the WAM API – which integrates into the existing Web Audio API – and provides its implementation for JavaScript and C++ bindings, and finds that the performance is sufficient for reasonable polyphony, depending on the complexity of the processing algorithms.
DAW Plugins for Web Browsers
It is found that ported DAW effect and sound synthesizer plugins complement and integrate with the Web Audio API, and that the existing preset patch collections make the plugins readily usable in online contexts.
Songle: A Web Service for Active Music Listening Improved by User Contributions
A public web service for active music listening, Songle, that enriches music listening experiences by using music-understanding technologies based on signal processing and proposes a mechanism of collaborative training for music- Understanding technologies, in which corrected errors will be used to improve the music- understanding performance through machine learning techniques.
Bringing the web up to speed with WebAssembly
The motivation, design and formal semantics of WebAssembly are described, some preliminary experience with implementations are provided, and it is described how WebAssembly is an abstraction over modern hardware, making it language-, hardware-, and platform-independent, with use cases beyond just the Web.
Emscripten: an LLVM-to-JavaScript compiler
This work presents and proves the validity of Emscripten's Relooper algorithm, which recreates high-level loop structures from low-level branching data, and opens up two avenues for running code written in languages other than JavaScript on the web.
Improving Audio Chord Transcription by Exploiting Harmonic and Metric Knowledge
A new system for chord transcription from polyphonic musical audio that uses domain-specific knowledge about tonal harmony and metrical position to improve chord transcription performance is presented and it is shown that exploiting metrical and harmonic knowledge yields statistically significant chord transcription improvements.
JSAP: A Plugin Standard for the Web Audio API with Intelligent Functionality
A standard framework which defines the plugin structure and host integration of a plugin is presented, which facilitates a novel method of cross-adaptive processing where features are transmitted between plugin instances instead of audio routing, saving on multiple calculations of features.