Signal Processing Engineer

Juhan Nam Curriculum Vitae

Ph.D. Candidate

Center for Computer Research in Music and Acoustics (CCRMA)

Music Department, Stanford University

*****@*****.********.***

http://ccrma.stanford.edu/~juhan

Education

2006-2012 Stanford University, CA, USA

(Expected) Ph.D. in Computer-Based Music Theory and Acoustics

Center for Computer Research in Music and Acoustics (CCRMA), Department of Music

(Advisor: Julius O. Smith III)2009-2010 Stanford University, CA, USA

M.S degree in Electrical Engineering

1994-1998 Seoul National University, Seoul, Korea

B.S. degree in Electrical Engineering

Work Experience

2011Sum Research Intern, Advanced Technology Labs, Adobe Systems, San Francisco, CA

- Research on sound recognition in mixtures for multimedia content analysis

2009-2011Research Assistant, CCRMA, Stanford University

- Feature representation by unsupervised learning for music information retrieval

- Band-limited filter design for virtual analog oscillator

- Head-related transfer function measurement and modeling for binaural sound processing

2010Sum Research Assistant, Suppes Brain Lab, Stanford University

- Feature learning and classification of EEG signals

2001-2006Software/DSP Engineer, Young Chang (Kurzweil Music Systems), Korea/Waltham, MA

- Developed software and DSP algorithm for music synthesizes and digital pianos

- Led software development for an award-winning musical keyboard

(Kurzweil SP2 - Electronic Musicians 2008 Editor s choice)

2000-2001Software Engineer, Cubic-I Inc., Seoul, Korea

- Developed audio editing software with 3-D sound effect

1998-2000Network Administrator, Nacssnet Inc., Seoul, Korea

- Managed network systems in SK Telecom, the largest mobile service company in Korea

Research Interests

- Machine learning and statistical modeling for audio processing and music analysis

- Digital signal processing for sound analysis, synthesis, and digital audio effect

- Physics-based musical instrument and acoustic modeling

- Software programming for audio/visual applications

Project/Research Experience

Machine Learning: Music/audio representation and recognition

- Automatic genre classification, annotation and retrieval

(

2011-current)

Automatic music genre classification / annotation and retrieval based on unsupervised

feature learning

and deep learning

- Sound recognition in mixtures for multimedia content analysis (2011)

Sound recognition in mixtures using a source separation method with temporal modeling

- Polyphonic piano transcription

(

2010-2011)

Music score generation from piano recordings using deep belief networks and a

classification-based

multi-pitch discrimination method

- Multi-modal speech recognition (2010)

Speech recognition using speech and video (lipreading) and unsupervised feature learning

- Super-resolution spectrogram (2010)

A new time-frequency representation method to achieve high resolution in time and

frequency

simultaneously using a probabilistic version of non-negative matrix factorization

Audio DSP

- Virtual analog synthesis (2009-2011)

Developed waveform interpolation algorithms for virtual analog oscillators. Several

polynomial -based

algorithms and optimization techniques were studied.

- Perceptual audio coding (2008)

Implemented an audio codec based on MDCT, perceptual modeling, Huffman and joint stereo

coding.

They were written in C and Python.

- Spatial audio processing (2007-2008)

Head-related transfer function (HRTF) measurement using a sine-sweep base method / HRTF

phase and

filter design study for efficient modeling. The model was implemented using OpenGL-based

graphic 3-

D user interface.

- Max/MSP (2005-2008)

Implemented virtual analog oscillators, audio filters and effects as audio plug-ins for

Max/MSP

Publications

2007-2009 Teaching Assistant, Stanford University

2012 Course: Audio Applications of the Fast Fourier Transform (Music421)

Perceptual Audio Coding (Music422)

Foundations of Sound Recording Technology (Music192A)

Element of Music II (Music22 musicianship)

Signal Processing Models in Musical Acoustics (Music420)

Introduction to Digital Audio Signal Processing (Music320)

2008 Instructor, CCRMA summer workshop, KAIST, Korea

Course: Introduction to Digital Audio Signal Processing

2006 Teaching Assistant, CCRMA summer workshop, Dongguk University, Korea

Course: Introduction to Digital Audio Signal Processing

2005 Instructor, Kurzweil Computer Music Camp, Baekseok University, Cheonan, Korea

Course: VAST Programming (Kurzweil synthesizer programming)

2003 Instructor, Kurzweil Computer Music Camp, Baekseok University, Cheonan, Korea

Course: VAST Programming (Kurzweil synthesizer programming)

Academic Awards

Stanford University Humanities and Sciences Fellowship, 2006-2007

Academic Review Activities

International Conference on Music Information Retrieval (ISMIR), 2012

International Computer Music Conference (ICMC), 2008

International Conference on Digital Audio Effect (DAFx), 2010

International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA),

2010

International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010, 2011,

2012

International Workshop on Advances in Music Information Research (AdMIRe), 2012

EURASIP Journal on Advances in Signal Processing, 2010

IEEE Transactions on Audio, Speech and Language Processing, 2010-2012

IEEE Signal Processing Letters, 2012

ELSEVIER Journal on Computer and Electrical Engineering, 2010

Academic Memberships

Student Member, IEEE - Signal Processing Society

Student Member, Audio Engineering Society (AES)

Student Member, International Speech Communication Association (ISCA)

Talks

2012 Jun Learning Feature Representations for Music Classification, Graduate School of

Culture

Technology, Korea Advanced Institute of Science and Technology (KAIST)

2012 Jun Learning Feature Representations for Music Classification, Graduate School of

Convergence Science and Technology, Seoul National University

2010 Oct A Super-Resolution Spectrogram Using Coupled PLCA, DSP Seminar, CCRMA, Stanford

University

2009 Mar Efficient Anti-aliasing Oscillators Using Polynomials, CCRMA open house,

Stanford

University

2009 Feb Efficient Implementation of Anti-aliasing Oscillators Using Low-Order Fractional

Delay

Filters, DSP Seminar, CCRMA, Stanford University

2008 Oct Minimum-phase nature of HRTFs and a method for estimating interaural time

difference

for binaural synthesis, DSP Seminar, CCRMA, Stanford University

Contact this candidate