Dynamic time warping for Pure Data

Authors: Pedro Lopes and Joaquim Jorge

Download full paper Media:Dynamic Time Warping for Pure Data.pdf

We present an implementation of the Dynamic Time Warping algorithm for the Pure Data programming environment. This algorithm is fairly popular in several contexts, ranging from speech processing to pattern detection, mainly because it allows to compare and recognize data sets that may vary non-linearly in time. Our contribution is easily portable to a wide number of platforms, where Pure Data is available. Throughout this document we describe relevant work that inspired our proposal and present the core concepts of our implementation.

Dtw help.png

We conclude with an evaluation of our Dynamic Time Warping implementation in two perspectives: performance and adequacy towards gesture recognition. The performance tests suggest that it is suited for realtime contexts, where algorithmic efficiency is of utmost importance. Finally we present a case study where our implementation was used successfully to accommodate gesture recognition on an existing application.

Hopefully with the feedback of the community this external can be released in a nearby future, allowing the DTW algorithm to be easily used from within Pd[[Pure Data]] a dataflow programming environment.

Early prototype video
Kreativfonds Bauhaus-Univeristät WeimarElectronic Arts Blog für digitale SpielkulturThe Mozilla FoundationAllied Vision TechnologiesReality Jockey Ltd.Freistaat ThüringenBauhaus-Universität WeimarHochschule für Musik Franz Liszt WeimarFraunhofer Institute for Digital Media Technology IDMTStadt WeimarKlassik Stiftung WeimarNKFaculty of MediaStudio for electro-acoustic MusicKulturTragWerk e.V.Elektronisches Studio der TU BerlinMaschinenraum Hackerspace WeimarParlomar5 e.V.Lab for Electronic Arts and PerformanceRadio Lotte WeimarSponsors and partners of the 4th internationals Pure Data Convention in Weimar 2011

4th international Pure Data Convention 2011 Weimar ~ Berlin