vjmedia - User contributions [en]

Musical Machine Learning

2016-05-05T05:53:21Z

Nsbradford: /* Musical Machine Learning */

=Musical Machine Learning=

[[File:Confutatis.png|600px]]

==Overview==

This project created a foundation for future work by WPI students in music information retrieval and machine learning. A Python system was first constructed to extract variable-length features from audio files. The problem of determining song structure was then approached with both supervised and unsupervised learning algorithms, resulting in a novel method for automated structure analysis. Finally, the groundwork was laid for the use of deep neural networks for musical composition.

==TODO List==

*Large additions
**Cluster an entire song in 1-s segments, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Musical Machine Learning

2016-05-05T05:52:23Z

Nsbradford: /* Musical Machine Learning */

=Musical Machine Learning=

[[File:Confutatis.png|200px]]

==Overview==

This project created a foundation for future work by WPI students in music information retrieval and machine learning. A Python system was first constructed to extract variable-length features from audio files. The problem of determining song structure was then approached with both supervised and unsupervised learning algorithms, resulting in a novel method for automated structure analysis. Finally, the groundwork was laid for the use of deep neural networks for musical composition.

==TODO List==

*Large additions
**Cluster an entire song in 1-s segments, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

File:Confutatis.png

2016-05-05T05:50:10Z

Nsbradford: Confutatis_Maledictis_RdBu_KNeighborsClassifier_2016-04-27_10-28-51.png

Confutatis_Maledictis_RdBu_KNeighborsClassifier_2016-04-27_10-28-51.png

Musical Machine Learning

2016-05-05T05:43:32Z

Nsbradford: /* TODO List */

=Musical Machine Learning=

==Overview==

This project created a foundation for future work by WPI students in music information retrieval and machine learning. A Python system was first constructed to extract variable-length features from audio files. The problem of determining song structure was then approached with both supervised and unsupervised learning algorithms, resulting in a novel method for automated structure analysis. Finally, the groundwork was laid for the use of deep neural networks for musical composition.

==TODO List==

*Large additions
**Cluster an entire song in 1-s segments, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Musical Machine Learning

2016-05-05T05:38:31Z

Nsbradford: /* Musical Machine Learning */

=Musical Machine Learning=

==Overview==

This project created a foundation for future work by WPI students in music information retrieval and machine learning. A Python system was first constructed to extract variable-length features from audio files. The problem of determining song structure was then approached with both supervised and unsupervised learning algorithms, resulting in a novel method for automated structure analysis. Finally, the groundwork was laid for the use of deep neural networks for musical composition.

==TODO List==

*Large additions
**Cluster an entire song in 1-s segements, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Musical Machine Learning

2016-05-05T05:37:28Z

Nsbradford:

=Musical Machine Learning=

[[File:LoopBuddy1.0.PNG|200px]]

==Overview==

This project created a foundation for future work by WPI students in music information retrieval and machine learning. A Python system was first constructed to extract variable-length features from audio files. The problem of determining song structure was then approached with both supervised and unsupervised learning algorithms, resulting in a novel method for automated structure analysis. Finally, the groundwork was laid for the use of deep neural networks for musical composition.

==TODO List==

*Large additions
**Cluster an entire song in 1-s segements, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Musical Machine Learning

2016-05-05T04:09:08Z

Nsbradford:

=Musical Machine Learning=

[[File:LoopBuddy1.0.PNG|200px]]

==Overview==

==TODO List==

*Large additions
**Cluster an entire song in 1-s segements, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
**Train a massive Deep Neural Net to try to automatically distinguish between parts
**Composition
***Create a LSTM recurrent neural net to learn from MIDI input
***Combine with Verse/Chorus algorithm/work to give songs more structure
***Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*Small improvements to Verse/Chorus system:
**Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
**Find additional features other than spectral centroid and zero-crossing rate
**IPython notebook demo (https://ipython.org/notebook.html)
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Musical Machine Learning

2016-05-05T04:03:32Z

Nsbradford:

=Musical Machine Learning=

==Overview==

==TODO List==

*Use SVM with linear kernel (instead of RBF) as a better approximation of "true" clustering
*Cluster an entire song in 1-s segements, then use a Gaussian KDE to smooth out classification. This can then be used to actually mark "segments" of a song
*Create website where people can upload a MIDI file, and then listen to RNN improvise over it
*IPython notebook demo
*Verse/Chorus system:
**Find additional features other than spectral centroid and zero-crossing rate
***Play with how the features are generated and averaged
**Include outlier detection in the data preprocessing stage
***(http://scikit-learn.org/stable/modules/outlier_detection.html)
**Optimize the different classifiers
**Optimize song loading times (store in database? alternative form?)
**Add option of multiple sections (bridge?)
*Expansions:
**Train a massive Deep Neural Net to try to automatically distinguish between parts
*Composition
**Create a LSTM recurrent neural net to learn from MIDI input
**Combine with Verse/Chorus algorithm/work to give songs more structure

==Help Connecting to Repository==

All files for this project are stored on the secured repository below. Contact Manzo for access once you've made an account on the Git (see Help).
 
Main project repository address:
 
http://solar-10.wpi.edu/ModalObjectLibrary/MachineLearning [git@solar-10.wpi.edu:ModalObjectLibrary/MachineLearning.git]

==WPI Student Contributors==
===2016===
Nicholas S. Bradford

 
[[Category: Advisor:Manzo]][[Category:Interactive Systems]]

Electronic Music Composition 2014

2014-10-15T14:04:10Z

Nsbradford:

==Electronic Music Composition==
Course files for ''Electronic Music Composition''
*[[How to Create Pages | How to Edit this Page]]

=Final Projects=

'''Student Name'''
''Demo Video Piece''

<mediaplayer>http://media.wpi.edu/Academics/Depts/HUA/Manzo/Soundbeam%20Chords/soundbeam.mp4</mediaplayer>
[http://media.wpi.edu/Academics/Depts/HUA/Manzo/Soundbeam%20Chords/SoundBeam_Chords.zip Source Files]

'''Another Student Name'''
''Demo Audio Piece''
<mp3player>http://media.wpi.edu/Academics/Depts/HUA/Manzo/White_Noise.mp3</mp3player>

'''Benjamin Duncan'''
''Time Traveler Jepsen''
<mp3player>http://wiki.wpi.edu/images//images/f/fe/Time_Traveler_Jepsen.mp3</mp3player>

'''Tyler Morrow'''
''Button Mashing''
<mp3player>http://media.wpi.edu/Academics/Depts/HUA/Manzo/_ Course Uploads/2014/Electronic Music Composition/Class 7/tyler-morrow--button_mashing.mp3</mp3player>

'''Jayson Corey'''
''Attack on Lorde''
https://my.wpi.edu/webapps/assignment/download?course_id=_66682_1&attempt_id=_1169649_1&file_id=_617892_1&fileName=Final_AttackOnLorde.wav

'''Paul Raynes'''
''Slam Warriors''
<mp3player>http://media.wpi.edu/Academics/Depts/HUA/Manzo/_ Course Uploads/2014/Electronic Music Composition/Class 7/Slam Warriors.mp3</mp3player>

'''Will Frick'''
''Stayin' Remixed''
<mp3player>http://wiki.wpi.edu/images//images/0/0f/Wofrick-final.mp3</mp3player>

'''Adam Karcs'''
''Demon Doges''
<mp3player>http://media.wpi.edu/Academics/Depts/HUA/Manzo/_ Course Uploads/2014/Electronic Music Composition/Class 7/Demon_Doges.mp3</mp3player>

'''Matthew Barreiro'''
''Make It Bun Dem (Rework)''
<mp3player>http://wiki.wpi.edu/images//images/9/9e/BarreiroFinalProject.mp3</mp3player>

'''Zitai huang'''
''Undead enemy (Remix)''
<mp3player>http://wiki.wpi.edu/images//images/3/35/Zitai_huang_final.mp3</mp3player>

'''Gareth Solbeck'''
''In Control (Max Patcher)''

[[File:Gareth_Solbeck-In_Control.png|400px|Presentation view]]

[[File:Gareth_Solbeck-In_Control_(full).png|400px|Editing view]]

[http://wiki.wpi.edu/images//images/4/4e/Gareth_Solbeck-In_Control.txt Source]

To use the patcher, copy the text and paste it into Max.
This patcher requires an XBox controller and the Controller driver available
[http://tattiebogle.net/index.php/ProjectRoot/Xbox360Controller/OsxDriver here].

'''Joshua Donovan'''
''Best of You (Remix)''
<mp3player>http://wiki.wpi.edu/images//images/0/01/Josh_Final.mp3</mp3player>

'''Ali Fuat Becan'
''Dance Glitch''

This is my last composition for the course as my MU362X Final Project. I first composed a dance song, repeating a pattern; then, I kick in a glitch to manipulate the entire audio chaotically, therefore creating an indirect reference to Glitch music genre.
<mp3player>http://wiki.wpi.edu/vjmedia/File:AFBecan_Final_Project_Dance_Glitch.mp3</mp3player>

'''Collin Glynn'''
''Rain Music Maker''
<mediaplayer>http://media.wpi.edu/Academics/Depts/HUA/Manzo/Rain Music Maker.cmproj</mediaplayer>

'''Nicholas S. Bradford'''
''Birth of a Villain (Original)''
<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>
[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]

http://media.wpi.edu/Academics/Depts/HUA/Manzo/White_Noise.mp3

[[Category:Electronic Music Composition (3620)]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:10:32Z

Nsbradford:

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X 2014 Final Project'''

This original piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

I used Finale and Audacity to produce the final audio. Here is the MP3 file of my composition:

<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>
[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:09:48Z

Nsbradford:

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X 2014 Final Project'''

This original piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

I used Finale and Audacity to produce the final audio. Here is the MP3 file of my composition:

[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]
<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:09:26Z

Nsbradford:

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X 2014 Final Project'''

This piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

I used Finale and Audacity to produce the final audio. Here is the MP3 file of my composition:

[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]
<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:06:35Z

Nsbradford:

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X Final Project'''

This piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

I used Finale and Audacity to produce the final audio. Here is the MP3 file of my composition:

[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]
<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:05:09Z

Nsbradford:

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X Final Project'''

This piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

Here is the MP3 file of my composition:

[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]
<mp3player>File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎‎</mp3player>

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

Final Project: Nicholas S. Bradford

2014-10-11T03:02:42Z

Nsbradford: Created page with ''''"Birth of a Villain" - Nicholas S. Bradford, MU 362X Final Project''' This piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the c…'

'''"Birth of a Villain" - Nicholas S. Bradford,
MU 362X Final Project'''

This piece was inspired by the fantasy novel that I am currently writing. It is meant to accompany the chapters in which the primary antagonist's origins are explained. The first half of the song is sad to to mirror the tragedies that happened to the villain early in his life, and the song takes a darker turn as the villain grows more and more evil. It eventually adds percussion to solidify the sinister tone. The song ends with the main theme repeated, percussion and snares added to give it a more aggressive and militaristic feeling, symbolizing how the villain is using the sad events of his early life to justify his acts of evil.

Here is the MP3 file of my composition:

[[File:NicholasBradford_FINAL_BirthOfAVillain.mp3‎]]
<mp3player>http://media.wpi.edu/Academics/Depts/HUA/Manzo/NicholasBradford_FINAL_BirthOfAVillain.mp3‎</mp3player>

----

[[Category:Scores and Arrangements]][[Category: Advisor:Manzo]]

File:NicholasBradford FINAL BirthOfAVillain.mp3

2014-10-11T02:59:09Z

Nsbradford: NicholasBradford_FINAL_BirthOfAVillain

NicholasBradford_FINAL_BirthOfAVillain