User Tools

Site Tools


intelligent_audio_switch_box

====== Differences ====== This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
intelligent_audio_switch_box [2014/10/26 14:10]
brechtdeman
intelligent_audio_switch_box [2014/10/28 22:51] (current)
brechtdeman Put HAMR hammer on bottom.
Line 16: Line 16:
  
 * **Simon-Claudius Wystrach** //​(remote)//​ Master student at University of York, United Kingdom * **Simon-Claudius Wystrach** //​(remote)//​ Master student at University of York, United Kingdom
 +
 +{{::​inasbteam.jpg|The team: Brecht, Nikolay, Simon-Claudius (remote) and Tom}}
 +
  
 ===== Features ===== ===== Features =====
  
-=== Plugin ===+==== Plugin ​====
  
-{{::inasbplugin.png|}}+{{::inasbpluginscreenshot.png|Screenshot of the plugin}}
  
-=== Parameters ===+==== Parameters ​====
  
-== GAIN == +=== GAIN === 
  - Amplification level of the input signal.  - Amplification level of the input signal.
  
-== THRESHOLD == +=== THRESHOLD ​=== 
  - The value of discrimination between channel A and B.  - The value of discrimination between channel A and B.
  
-== HYSTERESIS == +=== HYSTERESIS ​=== 
  - A noise gate that perpetuates the current state  - A noise gate that perpetuates the current state
  
-== INERTIA ==+=== INERTIA ​===
  - Determines how fast to apply parameter changes, for example, a high inertia setting will create a sweeping effect.  - Determines how fast to apply parameter changes, for example, a high inertia setting will create a sweeping effect.
  
  
-=== Learning ===+==== Learning ​====
 During the learning stage, four spectral features (centroid, flatness, crest and roll-off) are extracted from training examples. They are associated with one of the channels and stored in memory. The user would toggle "Train A" or "Train B" button and then produce sound for the plugin to learn from. The "​Finish"​ button completes the training stage, and the plugin becomes ready to route the signal. During the learning stage, four spectral features (centroid, flatness, crest and roll-off) are extracted from training examples. They are associated with one of the channels and stored in memory. The user would toggle "Train A" or "Train B" button and then produce sound for the plugin to learn from. The "​Finish"​ button completes the training stage, and the plugin becomes ready to route the signal.
  
-=== Playback ===+==== Playback ​====
 During the playback mode an algorithm finds the training example(s) nearest to the features extracted real-time from sound and the corresponding class routes the sound signal to the appropriate channel. During the playback mode an algorithm finds the training example(s) nearest to the features extracted real-time from sound and the corresponding class routes the sound signal to the appropriate channel.
  
Line 60: Line 63:
  
 ==== Distribution ==== ==== Distribution ====
-BitBucket Git repository is located at https://​bitbucket.org/​bogonetic/​inasbv1 
  
 To be released - stay tuned! ​ To be released - stay tuned! ​
Line 75: Line 77:
  
 {{::​inasbcode.png|}} {{::​inasbcode.png|}}
 +
 +//For this hack, our team received the prize for 'Best Code' - one of three HAMR trophies.//
 +{{::​iNASBhammer.jpg|'​Best Code' hammer, one of the three HAMR trophies.}}
intelligent_audio_switch_box.1414347053.txt.gz ยท Last modified: 2014/10/26 14:10 by brechtdeman