Difference between revisions of "DIA"

From CCRMA Wiki
Jump to: navigation, search
(Milestones)
(Design)
Line 20: Line 20:
  
 
== Design ==
 
== Design ==
* audio input will all be into one host computer
+
* Multi-track MIDI file loaded on start-up, to which voices are to be compared
* networked client computers will be able to receive channel-specific customized visualizations via OSC
+
* Multiple inputs connect to one host computer (Server/Director)
* performance error will be calculated with respect to user-provided midis of arrangements
+
* Networked client computers can connect to the Server
* pitch information will be determined by implementing a version of the YIN pitch detection algorithm  
+
* Clients will receive channel-specific data from the server
* tonal/vowel information will be provided by fft visualizations
+
* Clients may also listen in on data from other users
 +
* Performance error will be calculated with respect to deviation from MIDI arrangement
 +
* Pitch information will be determined by implementing a version of the YIN pitch detection algorithm
  
 
== Testing ==
 
== Testing ==

Revision as of 09:31, 10 December 2009

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

  • Multi-track MIDI file loaded on start-up, to which voices are to be compared
  • Multiple inputs connect to one host computer (Server/Director)
  • Networked client computers can connect to the Server
  • Clients will receive channel-specific data from the server
  • Clients may also listen in on data from other users
  • Performance error will be calculated with respect to deviation from MIDI arrangement
  • Pitch information will be determined by implementing a version of the YIN pitch detection algorithm

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
 - Charlie Forkish
 - Jay Bhat

Milestones (Revised)

  • DATE 1: 11/15 - accurate and robust implementation of YIN pitch detection algorithm with one input and playback of midi files
  • DATE 2: 12/4 - support for multiple inputs and polished visual feedback
  • DATE 3: 12/10 - distribution to multiple client computers over network and statistics report