Difference between revisions of "DIA"
From CCRMA Wiki
m (→Milestones) |
m (→Design) |
||
Line 24: | Line 24: | ||
* performance error will be calculated with respect to user-provided midis of arrangements | * performance error will be calculated with respect to user-provided midis of arrangements | ||
* pitch information will be determined by implementing a version of the YIN pitch detection algorithm | * pitch information will be determined by implementing a version of the YIN pitch detection algorithm | ||
− | * tonal/vowel information be provided by fft visualizations | + | * tonal/vowel information will be provided by fft visualizations |
− | + | ||
== Testing == | == Testing == |
Revision as of 15:20, 11 November 2009
Contents
DIA: Do It A Cappella
Idea / Premise
- a visual feedback system for a cappella singers to use alone or together as an ensemble
- a learning tool to train the voice and the ears
Motivation
- a large population of amateur a cappella singers who lack the necessary ear training to effectively self-correct
- the need for an objective method of performance evaluation to eliminate confusion over "who's hearing it right"
- a desire to explore basic real-time audio information retrieval techniques
What is DIA?
- an application for the real-time visualization of musical properties of one or more singers
- a network application allowing multiple singers to use laptops to see personalized visualizations provided by a host computer
- a vocal training application providing both real-time visualization of error and post-performance reports of achievement statistics
- a music learning tool for people who can't read music
Design
- audio input will all be into one host computer
- networked client computers will be able to receive channel-specific customized visualizations via OSC
- performance error will be calculated with respect to user-provided midis of arrangements
- pitch information will be determined by implementing a version of the YIN pitch detection algorithm
- tonal/vowel information will be provided by fft visualizations
Testing
- the harmonics, a stanford a cappella group, will be able to put DIA through comprehensive, rigorous testing
- effectiveness of execution will be judged based on the final product's ability to provide accurate and useful visual feedback to the user
Team
- the DIA team is comprised of charlie forkish and jay bhat
Milestones
- DATE 1: 11/15 - accurate and robust implementation of YIN pitch detection algorithm with one input and playback of midi files
- DATE 2: 11/25 - support for multiple inputs, polished visual feedback provided to client computers over network
- DATE 3: 12/4 - tone evaluation and achievement statistics report card