Projects

Projects

Research Projects @ MARL

Improving Access to Digital Music through Content-based Analysis

This project is a collaboration between MARL and NYU Library Services, concerned with the research and development of content-based approaches to the automatic organization of, access to and interaction with digital music archives.

Analyzing the Sequential Structure of Music Audio

This project aims at extending the understanding and usefulness of music data, through the research, development and application of computational approaches and tools. It advances an innovative and interdisciplinary program of research and education activities aimed at identifying the structures that define within- and between-song relationships in western tonal music; their applications to retrieval, visualization, music analysis and creation; and the dissemination of the knowledge base that makes these developments possible.

Gordon Music Database

Gordon is a Python-based system created to manage a centralized music catalog for research, including audio, meta-data, annotations, and signal features. It is mainly intended to support research in music information retrieval.

SIPLCA Segmentation

This package contains the implementation of the algorithm for identifying repeated harmonic patterns in music and structure segmentation. It is primarily written in Python but calls Matlab for feature extraction and performance evaluation.

Workshop: The Science of Music

An interactive after-school workshop for high school students

Head Related Impulse Response Repository

This HRIR repository is a collection of 113 dataset from 4 publicly available HRTF databases, namely the LISTEN, CIPIC, FIU and KEMAR-MIT. All datasets are converted to the MARL-NYU file format. No standardization process was applied to the measurements

ScanIR

ScanIR is an application for flexible multichannel impulse response measurement in Matlab, available for public distribution. The application interfaces with the PortAudio API using Psychtoolbox-3, a toolkit in Matlab allowing high-precision control of a multichannel audio interface. ScanIR contains single-channel, binaural, and multichannel input modes, and it also allows the use of multiple output test signals. It is hoped that this application will prove useful to researchers using Matlab for physical or psychological acoustic measurements.

Medical Imaging Sonification

The goal of this research project is to utilize sonification to examine the vast datasets yielded by current imaging techniques. The project aims to supplement current diagnosis techniques and reduce inter-observer variability in diagnoses and improve diagnostic capabilities. Currently, this research project focuses on PET scans of the human brain and the diagnosis of moderate to severe Alzheimer's disease.