emotionally-controlled music synthesis

22
Emotionally-Controlled Music Synthesis António Pedro Oliveira Amílcar Cardoso University of Coimbra, Portugal 12/12/2008

Upload: antonio-oliveira

Post on 12-Apr-2017

269 views

Category:

Engineering


0 download

TRANSCRIPT

Page 1: Emotionally-Controlled Music Synthesis

Emotionally-Controlled Music Synthesis

António Pedro OliveiraAmílcar CardosoUniversity of Coimbra, Portugal12/12/2008

Page 2: Emotionally-Controlled Music Synthesis

2

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 3: Emotionally-Controlled Music Synthesis

3

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 4: Emotionally-Controlled Music Synthesis

Introduction

4

Music is accepted as a language of emotional expression

To control this expression in an automatic way, we are developing a computational model that establishes relations between emotions and musical features

Emotions are defined in 2 dimensions: Valence: degree of happiness (from very sad to very happy

music) Arousal: degree of activation (from very relaxing to very

activation music)

Page 5: Emotionally-Controlled Music Synthesis

5

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 6: Emotionally-Controlled Music Synthesis

Computational Model – Features Extraction

6

Use a database of MIDI music labelled with symbolic and audio features

Page 7: Emotionally-Controlled Music Synthesis

Computational Model – Regression models

7

Use a database of MIDI music labelled with symbolic and audio features

Modelling relations between emotions and music features with regression models

Page 8: Emotionally-Controlled Music Synthesis

Computational Model

8

Use a database of MIDI music labelled with symbolic and audio features

Modelling relations between emotions and music features with regression models

Use these models to control the affective content of synthesized music

Page 9: Emotionally-Controlled Music Synthesis

Computational Model - Experiments

9

96 MIDI pieces of film music that last between 20 and 90 seconds

80 listeners Label online each affective

dimension with integer values between 0 and 10

Page 10: Emotionally-Controlled Music Synthesis

10

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 11: Emotionally-Controlled Music Synthesis

Features Extraction

11

Make a music base with MIDI music labelled with symbolic and audio features

Page 12: Emotionally-Controlled Music Synthesis

Features Extraction – Correlation between audio

features and valence

12

Sharpness – ratio of high/bass frequencies Loudness – total energy Flatness – spectral distribution of energy Dissonance – perceptive interference of

sinusoids

Page 13: Emotionally-Controlled Music Synthesis

Similarity – temporal spectral correlation of energy distribution by frequency bands

Dissonance – perceptive interference of sinusoids

Sharpness – ratio of high/bass frequencies Energy – total energy

Features Extraction – Correlation between audio

features and arousal

13

Page 14: Emotionally-Controlled Music Synthesis

Bridge the gap between audio and symbolic domain:

Spectral similarity vs. note duration, interonset interval Spectral dissonance vs. prevalence of percussion

instruments

Features Extraction – Correlation between audio and symbolic

features

14

Page 15: Emotionally-Controlled Music Synthesis

15

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 16: Emotionally-Controlled Music Synthesis

Regression models

16

Establish weighted relations between emotions and musical features

Use non-linear regression models Model with symbolic and audio

features

Page 17: Emotionally-Controlled Music Synthesis

Regression models – Correlation between models

and valence

17

Best hybrid (use of audio and symbolic features) non-linear regression model – 84%

Best symbolic linear regression model – 75% Best audio non-linear regression model – 61%

Page 18: Emotionally-Controlled Music Synthesis

Regression models – Best audio and symbolic features for

valence

18

Page 19: Emotionally-Controlled Music Synthesis

Regression models – Correlation between models

and arousal

19

Best hybrid (use of audio and symbolic features) non-linear regression model – 90%

Best symbolic linear regression model – 84% Best audio non-linear regression model – 75%

Page 20: Emotionally-Controlled Music Synthesis

Regression models – Best audio and symbolic features for

arousal

20

Page 21: Emotionally-Controlled Music Synthesis

21

Outline

Introduction Computational Model Features Extraction Regression Models Conclusion

Page 22: Emotionally-Controlled Music Synthesis

Conclusion

22

Hybrid non-linear regression models outperformed results of symbolic linear regression models

Non-linear models seem more appropriate than linear models

The use of features from audio and symbolic domains is more appropriate than the use of features from only one domain

Timbre/sound can be used to control/influence the emotional expression