Ricardo A. Garcia
rago @ ragomusic.com
Last updated on 6/11/2017
Objective Very diverse senior software engineer with strong background in digital signal processing offering innovative ideas for audio, video, media and information management industries.

Work in a highly motivated scientific environment, involved with research/development of novel ideas for the audio/music/video/media/information industries.



Realtime sound processing in mobile platforms (Android, iOS), hearing health, sound synthesis, algorithmic representation of DSP routines, DSP for sound modeling, psychoacoustics, sound, music and media encoding/decoding, audio watermarking and data hiding, modular architecture for computer systems, cognitive models for music and sound, evolutionary computation, music information retrieval, music similarity, automated music recommendations, online communities.
Detailed work experience



Google           Senior Software Engineer June 2014 – Present
Mountain View, CA
Android Audio Framework Team

  • Contribute to the Android Open Source Project
  • Design and implementation of APIs for audio control, routing, processing in java, C and C++.
  • Design and implementation of psychoacoustic tests for audio quality assessment.
  • Custom code for Google Android proprietary devices (Nexus, Pixel)
  • Designed and implemented new sources for audio acquisition in android devices, useful for scientific measurements.
  • Designed and implemented SDK for audio signal processing for android framework.
  • Interview software engineering candidates for Android teams and Google in general.


Founder & CTO       
August 2009 – June 2014
Somerville, MA; Chicago IL
Consulting services for signal processing software design and implementation. Solves esoteric audio and media related problems for a variety of companies, such as:



–       Design and implementation of audio Processing plug-ins for Xbox sdk (auto filter, beat repeater, etc).


–       Head of research for “audio forensics”: analysis of mp3 and aac files for traces of authenticity and other identifiable information

–       Developed full fingerprinting system for 10+ Million songs.

–       Systems architecture design for large transaction volume.

Source Audio

–       Design and implementation of pc/mobile audio effect plugin library manager for next generation guitar effects.

–       Design and implementation of Hot Hand USB software companion for windows/mac.


–       Design and implementation of cross platform tinnitus synthesizer and audio processing filter for medical treatment.

–       iOS media player with realtime sound processing.


– Design and implementation of new RichMix algorithm for playlist creation.

Hearing Aid Manufacturer (unnamed)

–       Design and implementation of low level sdk for wireless earpiece control for iOS.

–       Framework sdk documentation and example apps for third party developers.


–       Integration of the Base 10 Labs iOS realtime SDK .

–       Custom Multiband compressor for Hearing Aid simulation


In-house technologies and products:

– Realtime Audio Watermarking

– Cross Platform signal processing framework, with iOS realtime DSP sdk for licensing.

– SpecttroGuard: iOS application to change media player behavior based on acoustic context of the user’s location.


Senior Software Engineer
September 2007 – November 2010
Waltham, MA
Main Roles:

Embedded programmer using C and C++ for the PC3 synthesizer/controller series.
Architect for the controller system in the new generation of products.



Designed and implemented a modular sequencer architecture:

– Capabilities for many sequencers running simultaneously.

– Cross-sequencer synchronization, triggering, etc. (riffs in the new Kurzweil products)

– Cross platform code: embedded, linux, windows, mac.

– Embedded UI for sequence creation and editing.



Principal Architect for the New Editor System

– Cross platform: embedded, windows, linux, mac.

– Separation between UI elements and parameters using a remote addressing system.

– Implemented the whole navigation, rendering engine for the embedded system.

– using an external (custom created) WYSIWYG editor to create all the UI.

– Created and tested the new concepts with a remote virtual display and control system, capable of fully controlling PC3 series of synthesizers using TPC/IP or serial communication.


Low Level Tools:

– Rewrote all the dynamic memory (malloc) functions.

– Tools to measure the performance of the system

– Tools for detecting memory leaks, bad memory usage practice, etc.


Audio Analysis:

– Use of high resolution spectral analysis and parameter estimation to find similar sounds in synthesizers.

– Genetic Programming tools to create new sounds by example.




GROOVE MOBILE       Audio Scientist
(formerly Chaoticom)        
November 2001 – August 2007
Hampton Falls, NH; Andover, MA.; Bedford MA
Work in a small scientific team researching and developing algorithms for high quality low bitrate audio encoding.

  • Development and implementation of:
    • Custom psychoacoustic models for analysis and synthesis of audio and music signals.
    • Various joint stereo (and multichannel) algorithms for sound compression.
    • Integer FFT algorithms.
    • High resolution analysis and synthesis
    • Representation of transient events by means of modeling of the phase.
    • Many ‘in-house’ tools for debugging of Matlab and C++ code.
    • GUI for audio encoding software, management of audio tracks.
    • ID3 tag editor
    • Tools for benchmarking of audio encoders
    • Preprocessing tools (level, eq, dynamics) for automatic content encoding.
  • Detection, isolation and correction of various audio artifacts by means of critical listening.
  • Sound quality assessment.
  • Development of guidelines for perceptual listening tests.
  • Mentoring and supervision of graduate level interns.

Development and implementation of high quality low bitrate video encoding algorithms.

  • Adaptation and further research of audio analysis techniques into multiple dimensions tailored for video applications.

Development and implementation of “music recommendation” system.

  • Development of an efficient real-time sparse matrix library capable of handling millions of cross referenced items.
  • Research and implementation of correlation and music similarity metrics.

Design and implementation of the “Online Community” system.

  • Profile based online community for networking.
  • Focused on playlist sharing, profile matching based on multiple criteria (profile, playlists, artist, genre)
  • Modular design: webservice backend + presentation layer (html/wap/proprietary)


MIT MEDIA LAB         Research Assistant September 1999 – September 2001
Cambridge, MA
  • Designed and implemented a full Genetic Programming environment to evolve Sound Synthesis Algorithms. (AGeSS system)
    • Syntax and grammar for manipulation of Sound Synthesis Algorithms (SSA) as topologies
    • Generation mechanism to create valid SSAs
    • Development and integration of a psychoacoustic algorithm to evaluate the subjective performance of various SSAs
  • Setup for controlling multiple DVD players synchronized for the “in place performers” exhibition.
  • Developed a system to use Cellular Automata as sound synthesizers, and a method to train the system by using psychoacoustic models.
  • Developed a sound classification system by use of Cepstral coefficients grouping.
  • Involved in the definition of a Melody Contour descriptor proposed to the MPEG-7 Standards Committee.
  • Several talks and publications about the uses of Genetic Programming for sound synthesis and audio processing.
  • Presentation, demos and talks about the research performed at the Machine Listening group at MIT Media Lab (netsound, structured audio, instrument recognition, voice modeling, music modeling).


UNIVERSITY OF MIAMI                     Teaching Assistant

School of Music

May 1998 – May 1999
Coral Gables, FL
  • Designed and implemented an audio watermarking algorithm capable of embedding an imperceptible stream of bits in audio signals.
  • Designed and implemented psychoacoustic models of human hearing mechanism.
  • Explored the use of spread spectrum techniques to encode bit streams in audible frequency range signals.
  • Designed and implemented a system for voice removal from audio recordings by using adaptive filtering.
  • Designed a test for subjective evaluation of perceived audio quality and artifact detection of psychoacoustically modified audio.
  • Supported and enhanced the Real Audio system for internet broadcasting of live concerts. Added automatic scheduling, logging and archiving of concerts. Upgraded and configured system to use the latest available low bitrate encoders.
  • Served as Network Administrator for the school of music computer network. Responsible for: main server, web server, and two audio computer labs.


LA FACTORIA            Music Engineer, co-owner December 1996 – August 1997
Medellin, Colombia
  • Studio for production, recording, mixing, mastering and post-production.


VIA MIDI                     Music Engineer, owner June 1994 – August 1997
Medellin, Colombia
  • Taught courses in music sequencing, audio production, home studio recording, audio processing, and general use of computer for music production.
  • Consultant for multiple professional audio setups.
  • Designed, implemented and manufactured MIDI interfaces for pc computers.
Computer Tools


  • Programming and simulation software: C++, C, Java (Android), Objective C (iOS), Matlab, Qt, wxWidgets
  • Sound Editing/processing: Audition, Studio One, Cooledit, sound forge, Sonar, Pure Data, FX
  • OS: Windows, Mac, Linux
  • Mobile OS: iOS, Android (java and native)
  • Virtualization tools: VMWare server, Virtual box.
  • Most of windows office tools
  • Internet: JSP, Servlets, php, html, wml, MongoDB, MySQL, Tomcat, Apache, Velocity, Node.js
  • Graphic software: Adobe Photoshop, Illustrator, Corel Draw, InkScape
  • Microcontrollers/DSP : Zilog Z8, Motorola 5600 family, SH3, SH2A, ADI sigma dsp.


Education Massachusetts Institute of Technology (MIT), Cambridge MA

Master of Science in Media Arts and Sciences, September 2001, GPA: 3.9/4.0

Master’s thesis title: Automatic Generation of Sound Synthesis Techniques


University of Miami, Coral Gables, FL

Master of Science in Music Engineering, May 1999, GPA: 3.93/4.0

Master’s thesis title: Digital Watermarking of Audio Signals using Psychoacoustic and Spread Spectrum Techniques

– Scholarship granted by COLCIENCIAS and LASPAU.

– Award of Academic Merit by the Dean of the Graduate School, May 1999


Universidad Pontificia Bolivariana (UPB), Medellin, Colombia S.A.

Bachelor of Science in Electronic Engineering, December 1996, GPA: 4.05 / 5.0

Bachelor thesis title: Platform for the Digital Signals Processing of audio signals: Pitch shifting algorithm.

Relevant Courses


DSP, Acoustics, Psychoacoustics, Sound Synthesis, Adaptive DSP, Speech Processing, Pattern Recognition, Machine Learning, Control Systems, Mathematical Modeling, Loudspeaker Design, Network Communications, Cognitive Models, Mechatronics
Related Activities


Audio Engineering Society (AES) member

Señal Nocturna (Music Band) : Composer (words and music), Keyboards, recording engineer, sequences, programming, musical production, mastering.

Other Activities Photography, writing, music playing and composition (piano, electronic music).
Selected Publications


R. Garcia, “Browser that Archives Webpages”, Technical Disclosure Commons, (May 12, 2017)

Short, K., Garcia, R., Daniels, M. (2007). “Multi-Channel Audio Processing Using a Unified Domain Representation”, J. Audio Eng. Soc. Volume 55 Issue 3 pp. 156-165; March 2007

Short, K. and Garcia, R. (2006) “Accurate Low-Frequency Magnitude and Phase Estimation in the Presence of DC and Near-DC Aliasing”, 121st Convention, Audio Engineering Society, San Francisco, , October 5-8, 2006. Preprint 6934

Short, K. and Garcia, R. (2006) “Signal Analysis Using the Complex Spectral Phase Evolution (CSPE) Method”, 120th Convention, Audio Engineering Society, Paris, France, May 20-23, 2006. Preprint 6645

Short, K., Garcia, R., Daniels, M. (2005). “Multichannel Audio Processing Using a Unified Domain Representation”, 119th Convention, Audio Engineering Society, New York, NY, October 7-10, 2005.   Preprint 6526

Short, K., Garcia, R., Daniels, M. (2005). “Scalability in KOZ Audio Compression”, 119th Convention, Audio Engineering Society, New York, NY, October 7-10, 2005. Preprint 6598

Short, K., et. al (2005). “An Introduction to the KOZ Scalable Audio Compression Technology”, 118th Convention, Audio Engineering Society, Barcelona, Spain, May 28 – 31, 2005. Preprint 6446

Short, K., et al (2005), “Methods and systems for digital rights management of protected content”, United States Patent Application 20050021539, January 27, 2005

Garcia, R. (2002). “Automatic Design of Sound Synthesis Techniques by means of Genetic Programming”, 113th Convention, Audio Engineering Society, Los Angeles, CA, October 5-8, 2002.   Preprint 5654

Garcia, R. (2001). “Automating the Design of Sound Synthesis Techniques using Evolutionary Methods”,   Proceedings of the COST G-6 Conference on Digital Audio Effects (DAFX-01), Limerick, Ireland, December 6-8, 2001

Garcia, R. (2001). “Automatic Generation of Sound Synthesis Techniques”, Master of Science Thesis, Master in Media Arts and Sciences, School of Architecture and Planning, Massachusetts Institute of Technology, Cambridge, MA, September 2001

Garcia, R. (2001). “Growing Sound Synthesizers using Evolutionary Methods”, to be presented in European Conference in Artificial Life 2001 (ECAL2001) special workshop in Artificial Life Models for Musical Applications to be held in University of Economics, Prague, Czech Republic, September 9 2001

Garcia, R. (2000). “Towards the Automatic Generation of Sound Synthesis Techniques: Preparatory Steps”, 109th Convention, Audio Engineering Society, Los Angeles, CA, September 22 -25, 2000. Preprint 5186

Kim, Y. E., Chai, W., Garcia, R., Vercoe, B. (2000).”Analysis of a Contour-based Representation for Melody”, International Symposium on Music Information Retrieval, Plymouth, MA, October 23 – 25, 2000

Garcia, R. (1999). “Digital Watermarking of Audio Signals using a Psychoacoustic Auditory Model and Spread Spectrum Theory”, 107th Convention, Audio Engineering Society, New York, NY, September 24-27, 1999. Preprint 5073

Garcia, R. (1999). “Digital Watermarking of Audio Signals using a Psychoacoustic Auditory Model and Spread Spectrum Theory”, Master of Science Thesis, Music Engineering Technology, University of Miami, Coral Gables, FL, April 21, 1999

Selected Patents A. Sabin, R. Garcia “Processing Multichannel Audio Signals,” U.S. Patent: 9454970, issued date September 27, 2016

K. Short, R. Garcia, M. Daniels, J. Curley “Systems and methods for high resolution signal analysis and chaotic data compression,” U.S. Patent Application: 11441791, publication date November 30, 2006

K. Short, P. Dorward, R. Garcia, B. Hunt, M. Glover, J. Curley, J. Struven, M. Gallagher “Methods and systems for digital rights management of protected content,” U.S. Patent Application: 10794571, publication date January 1, 2005

References Available upon request.