SlideShare ist ein Scribd-Unternehmen logo
1 von 103
E N G A G I N G T H E W O R L D
Automatic Calibration of Modified FM Synthesis
to Harmonic Sounds using Genetic Algorithms
Matthieu Macret - Philippe Pasquier - Tamara Smyth
Replicating sounds of musical instruments
• Problem frequently addressed in Computer
Music
• Various synthesis techniques developed over
the past century (Additive, FM, granular...)
2
Issues / Limitations
• Parametric Synthesis techniques
• Selecting suitable controls and synthesis
parameters can be unintuitive, manual and
time consuming
3
Automatic calibration
• Genetic algorithms
• Neural networks
• Cellular automata
• Particle Swarm Optimization
• etc.
4
Scope of our research
• Genetic algorithms (GA)
• Modified FM synthesis
• Musical harmonic sounds
5
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
6
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
7
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
FM synthesis
Classic	
  FM	
  synthesis:
Chowning	
  
(AES	
  Journal	
  1973)
Modified	
  FM	
  synthesis:
Lazzarini,	
  V.	
  and	
  Timoney	
  
(AES	
  Journal	
  2010)
8
Synthesis Model
9
Synthesis Model
9
Synthesis Model
9
Synthesis Model
9
Synthesis Model
9
Synthesis Model
Insure	
  the	
  harmonicity	
  of	
  the	
  sound
Scale	
  spectum	
  on	
  the	
  target	
  sound	
  spectrum
9
Parameters to optimize
k1 I1 k2 I2 ... kN IN
Param. Bounds Type Use
k [0,10] Integer
I [0,20] Double
10
Input parameters
• number of carriers
• harmonic target sound
11
Genetic Algorithm
12
Image	
  from	
  www.genePc-­‐programming.com
Initialization
13
PopulaPon	
  size	
  =	
  100
Initialization
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
13
PopulaPon	
  size	
  =	
  100
Evaluation
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
14
Evaluation
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
14
Evaluation
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
14
Evaluation
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
6
3 1
2
4
2
7
6
4
14
E N G A G I N G T H E W O R L D
Fitness function
Analysis parameters
Analysis window size 10	
  ms
Overlapping 5	
  ms
Zero padding factor 4
Spectral resolution 20	
  Hz
16
Target	
  Sound
Fitness function
17
Target	
  Sound
Fitness function
17
Target	
  spectrum
A
Hz
18
Target	
  spectrum
A
Hz
18
Target	
  spectrum
A
Hz
Target	
  vector
18
k1 I1 k2 I2 k3 I3
19
k1 I1 k2 I2 k3 I3
19
k1 I1 k2 I2 k3 I3
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
Hz
A
19
k1 I1 k2 I2 k3 I3
Hz
A
Hz
A
19
20
System	
  of	
  equaPons	
  to	
  solve
Unknown
Least	
  Squares	
  ApproximaPons
Fitness	
  Func:on	
  +=	
  approximaPon	
  error
21
Target	
  Sound
22
Target	
  Sound
22
Target	
  Sound
22
1st	
  Carrier	
  envelop	
  
3st	
  Carrier	
  envelop	
  
2st	
  Carrier	
  envelop	
  
Synthesized	
  sound:
23
Fitness	
  Func:on	
  =	
  sum(approximaPon	
  errors)
Termination
criteria
• Reach 300
generations
• Weighted change in
the fitness < 1.E-10
over 50 generations
24
GeneraPon	
  0:	
  Size	
  =	
  100
2	
  elites	
  
children
0.8	
  x	
  98	
  =	
  78	
  children	
  
by	
  crossover
98-­‐78	
  =	
  20	
  children	
  
by	
  mutaPon
GeneraPon	
  1:	
  Size	
  =	
  100
25
Generating the next population
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
6
3 1
2
4
2
7
6
4
26
Binary selection tournament
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
6
3 1
2
4
2
7
6
4
26
Binary selection tournament
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN
6
3 1
2
4
2
7
6
4
26
Binary selection tournament
Crossover
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
k1 I1 k2 I2 ... kN IN
Parents
Children
Crossover	
  point
27
Gaussian Mutation Operator
k1 I1 k2 I2 ... kN IN
Add	
  a	
  random	
  number	
  from	
  a	
  gaussian	
  
distribuPon
28
Termination
criteria
• Reach 300
generations
• Weighted change in
the fitness < 1.E-10
over 50 generations
29
Evaluations
1.Musical Instrument Sounds (University of
Iowa Electronic Music Studios)
2.Comparison between ClassicFM and ModFM
30
Insure	
  the	
  harmonicity	
  of	
  the	
  sound
Scale	
  spectum	
  on	
  the	
  target	
  spectrum
31
Musical Instrument Sounds
• AltoSax
• Bass
• Bassoon
• Clarinet
• Cello
• Flute
• Violin
32
• Horn
• Oboe
• Piano
• Tenor Trombone
• Trumpet
• Tuba
• Viola
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 368 180 121
nb	
  Gen	
  to	
  converge 69 138 58
Results Flute - ModFM
33
Flute - Harmonic 1 34
Flute - Harmonic 4 35
Flute - Harmonic 6 36
Flute - Harmonic 9 37
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
Results Clarinet - ModFM
38
Target
Number	
  of	
  carriersNumber	
  of	
  carriersNumber	
  of	
  carriers
Target
2 4 6
Best	
  fitness	
  score 20.8 8.50 3.9
nb	
  Gen	
  to	
  converge 71 64 75
39
Clarinet Spectra
20.8
8.50
3.9
Fitness
Stats ClassicFM - ModFM
40
ParametersParameters
ClassicFMClassicFM ModFMModFM
mean SD mean SD
Fitness
Gen.	
  to	
  conv.
51.94 77.96 52.60 87.52
99.24 69.24 87.60 42.57
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Trumpet - 6 carriers 41
Stats Evolution 42
Contributions
• Apply GA to a new FM synthesis technique
• Automatize completely the process
• Refine the parameters of the GA
• Evaluation on a large set of sounds
• Comparison between ClassicFM and ModFM
43
Future work - GA
• Remove constraints:
–Non harmonic sounds
–Remove constraint on the synthesis method
–Other fitness function
44
Future work - GP
• Go further!
• Evolve not only the
parameters but also
the synthesis model
45
http://www.metacreation.net/mume2012/
46Chair
Philippe	
  Pasquier
Co-­‐Chairs
Arne	
  Eigenfeldt,	
  Olivier	
  Brown
E N G A G I N G T H E W O R L D
Thank you !
Matthieu Macret - Philippe Pasquier - Tamara Smyth
mmacret@sfu.ca - pasquier@sfu.ca - tamaras@sfu.ca

Weitere ähnliche Inhalte

Kürzlich hochgeladen

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 

Kürzlich hochgeladen (20)

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 

Empfohlen

2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by HubspotMarius Sescu
 
Everything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTEverything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTExpeed Software
 
Product Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsProduct Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsPixeldarts
 
How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthThinkNow
 
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfAI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfmarketingartwork
 
PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024Neil Kimberley
 
Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)contently
 
How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024Albert Qian
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsKurio // The Social Media Age(ncy)
 
Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Search Engine Journal
 
5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summarySpeakerHub
 
ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd Clark Boyd
 
Getting into the tech field. what next
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next Tessa Mero
 
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentLily Ray
 
Time Management & Productivity - Best Practices
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best PracticesVit Horky
 
The six step guide to practical project management
The six step guide to practical project managementThe six step guide to practical project management
The six step guide to practical project managementMindGenius
 
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...RachelPearson36
 

Empfohlen (20)

2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot
 
Everything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTEverything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPT
 
Product Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsProduct Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage Engineerings
 
How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental Health
 
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfAI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
 
Skeleton Culture Code
Skeleton Culture CodeSkeleton Culture Code
Skeleton Culture Code
 
PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024
 
Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)
 
How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie Insights
 
Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024
 
5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary
 
ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd
 
Getting into the tech field. what next
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next
 
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search Intent
 
How to have difficult conversations
How to have difficult conversations How to have difficult conversations
How to have difficult conversations
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Time Management & Productivity - Best Practices
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best Practices
 
The six step guide to practical project management
The six step guide to practical project managementThe six step guide to practical project management
The six step guide to practical project management
 
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
 

Automatic Calibration of Modified FM Synthesis to Harmonic Sounds using Genetic Algorithms

  • 1. E N G A G I N G T H E W O R L D Automatic Calibration of Modified FM Synthesis to Harmonic Sounds using Genetic Algorithms Matthieu Macret - Philippe Pasquier - Tamara Smyth
  • 2. Replicating sounds of musical instruments • Problem frequently addressed in Computer Music • Various synthesis techniques developed over the past century (Additive, FM, granular...) 2
  • 3. Issues / Limitations • Parametric Synthesis techniques • Selecting suitable controls and synthesis parameters can be unintuitive, manual and time consuming 3
  • 4. Automatic calibration • Genetic algorithms • Neural networks • Cellular automata • Particle Swarm Optimization • etc. 4
  • 5. Scope of our research • Genetic algorithms (GA) • Modified FM synthesis • Musical harmonic sounds 5
  • 6. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 6
  • 7. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 8. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 9. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 10. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 11. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 12. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 13. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 7
  • 14. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 15. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 16. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 17. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 18. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 19. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 20. FM synthesis Classic  FM  synthesis: Chowning   (AES  Journal  1973) Modified  FM  synthesis: Lazzarini,  V.  and  Timoney   (AES  Journal  2010) 8
  • 26. Synthesis Model Insure  the  harmonicity  of  the  sound Scale  spectum  on  the  target  sound  spectrum 9
  • 27. Parameters to optimize k1 I1 k2 I2 ... kN IN Param. Bounds Type Use k [0,10] Integer I [0,20] Double 10
  • 28. Input parameters • number of carriers • harmonic target sound 11
  • 29. Genetic Algorithm 12 Image  from  www.genePc-­‐programming.com
  • 31. Initialization k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 13 PopulaPon  size  =  100
  • 32. Evaluation k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 14
  • 33. Evaluation k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 14
  • 34. Evaluation k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 14
  • 35. Evaluation k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 6 3 1 2 4 2 7 6 4 14
  • 36. E N G A G I N G T H E W O R L D Fitness function
  • 37. Analysis parameters Analysis window size 10  ms Overlapping 5  ms Zero padding factor 4 Spectral resolution 20  Hz 16
  • 43. k1 I1 k2 I2 k3 I3 19
  • 44. k1 I1 k2 I2 k3 I3 19
  • 45. k1 I1 k2 I2 k3 I3 Hz A 19
  • 46. k1 I1 k2 I2 k3 I3 Hz A 19
  • 47. k1 I1 k2 I2 k3 I3 Hz A 19
  • 48. k1 I1 k2 I2 k3 I3 Hz A 19
  • 49. k1 I1 k2 I2 k3 I3 Hz A Hz A 19
  • 50. k1 I1 k2 I2 k3 I3 Hz A Hz A 19
  • 51. k1 I1 k2 I2 k3 I3 Hz A Hz A 19
  • 52. 20
  • 53. System  of  equaPons  to  solve Unknown Least  Squares  ApproximaPons Fitness  Func:on  +=  approximaPon  error 21
  • 57. 1st  Carrier  envelop   3st  Carrier  envelop   2st  Carrier  envelop   Synthesized  sound: 23 Fitness  Func:on  =  sum(approximaPon  errors)
  • 58. Termination criteria • Reach 300 generations • Weighted change in the fitness < 1.E-10 over 50 generations 24
  • 59. GeneraPon  0:  Size  =  100 2  elites   children 0.8  x  98  =  78  children   by  crossover 98-­‐78  =  20  children   by  mutaPon GeneraPon  1:  Size  =  100 25 Generating the next population
  • 60. k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 6 3 1 2 4 2 7 6 4 26 Binary selection tournament
  • 61. k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 6 3 1 2 4 2 7 6 4 26 Binary selection tournament
  • 62. k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN INk1 I1 k2 I2 ... kN IN 6 3 1 2 4 2 7 6 4 26 Binary selection tournament
  • 63. Crossover k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN k1 I1 k2 I2 ... kN IN Parents Children Crossover  point 27
  • 64. Gaussian Mutation Operator k1 I1 k2 I2 ... kN IN Add  a  random  number  from  a  gaussian   distribuPon 28
  • 65. Termination criteria • Reach 300 generations • Weighted change in the fitness < 1.E-10 over 50 generations 29
  • 66. Evaluations 1.Musical Instrument Sounds (University of Iowa Electronic Music Studios) 2.Comparison between ClassicFM and ModFM 30
  • 67. Insure  the  harmonicity  of  the  sound Scale  spectum  on  the  target  spectrum 31
  • 68. Musical Instrument Sounds • AltoSax • Bass • Bassoon • Clarinet • Cello • Flute • Violin 32 • Horn • Oboe • Piano • Tenor Trombone • Trumpet • Tuba • Viola
  • 69. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 70. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 71. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 72. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 73. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 74. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 75. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 76. Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 368 180 121 nb  Gen  to  converge 69 138 58 Results Flute - ModFM 33
  • 81. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 82. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 83. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 84. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 85. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 86. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 87. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 88. Results Clarinet - ModFM 38 Target Number  of  carriersNumber  of  carriersNumber  of  carriers Target 2 4 6 Best  fitness  score 20.8 8.50 3.9 nb  Gen  to  converge 71 64 75
  • 90. Stats ClassicFM - ModFM 40 ParametersParameters ClassicFMClassicFM ModFMModFM mean SD mean SD Fitness Gen.  to  conv. 51.94 77.96 52.60 87.52 99.24 69.24 87.60 42.57
  • 91. Trumpet - 6 carriers 41
  • 92. Trumpet - 6 carriers 41
  • 93. Trumpet - 6 carriers 41
  • 94. Trumpet - 6 carriers 41
  • 95. Trumpet - 6 carriers 41
  • 96. Trumpet - 6 carriers 41
  • 97. Trumpet - 6 carriers 41
  • 99. Contributions • Apply GA to a new FM synthesis technique • Automatize completely the process • Refine the parameters of the GA • Evaluation on a large set of sounds • Comparison between ClassicFM and ModFM 43
  • 100. Future work - GA • Remove constraints: –Non harmonic sounds –Remove constraint on the synthesis method –Other fitness function 44
  • 101. Future work - GP • Go further! • Evolve not only the parameters but also the synthesis model 45
  • 103. E N G A G I N G T H E W O R L D Thank you ! Matthieu Macret - Philippe Pasquier - Tamara Smyth mmacret@sfu.ca - pasquier@sfu.ca - tamaras@sfu.ca