Synthesis of sound effects for generative animation
Tatsuo Unemi: Synthesis of sound effects for generative animation. In: Generative Art 2012, 364-376.
As everyone knows, the sound effect and background music of motion picture is effective to emphasize what the author wanted to express. However, in case of fully automated generative animation, it is difficult to introduce such a method for design of accompanying sounds because the generator has no intention behind the process. This paper introduces a method to synthesize waveforms of sounds for an automated evolutionary animation [1, 2] by computer. To emphasize the emotional effects for viewers, it was designed as to fit the psychological effect of sounds with visuals under some intuitive correspondences between these two different modalities, such as a brighter image is associated with a higher pitch, a more complex texture inspires a noisier or more solid tone, and so on. The other mappings between statistical features of image and parameters of sound synthesis and modulation are also effective to produce richer audio outputs. In addition, the two types of restriction on pitches for the scale and on timing for the rhythm were also examined for automatic music composition. There are many potential applications and extensions from this research, including evolutionary production of sound effects, as future works.
1. Tatsuo Unemi: SBArt4 as Automatic Art and Live Performance Tool, in C. Soddu ed. Proceedings of the 14th Generative Art Conference, pp. 436–447, December 4–7, Rome, Italy, 2011.
2. Tatsuo Unemi: SBArt4 for an Automatic Evolutionary Art, Proceedings of the IEEE World Congress on Computational Intelligence (WCCI 2012 – IEEE CEC 2012), pp. 2014–2021, June 10–15, Brisbane, QLD, Australia, 2012.
3. Scott D. Lipscomb and Roger A. Kendall: Perceptual Judgement of the Relationship between Musical and Visual Components in Film, Psycho- musicology, No. 13, pp. 60–98, 1994.
4. William Moss, Hengchin Yeh, Jeong-Mo Hong, Ming C. Lin and Dinesh Manocha: Sounding Liquids: Automatic Sound Synthesis from Fluid Simulation, ACM Transactions on Graphics, Vol. 28, No. 4, Article 110, December 2009.
5. Yoshinori Dobashi, Tsuyoshi Yamamoto and Tomoyuki Nishita: Synthesizing Sound from Turbulent Field using Sound Textures for Interactive Fluid Simulation, Eurographics, Vol. 23, No. 3, 2004.
6. Roger B. Dannenberg, Barbara Bernstein, Garth Zeglin and Tom Neuendorffer: Sound Synthesis from Video, Wearable Lights, and ‘The Watercourse Way,’ Proceedings: The Ninth Biennieal Symposium on Arts and Technology, New London, CT: Ammerman Center for Arts and Technology, pp. 38–44, 2003.
7. Tatsuo Unemi: SBArt4 Daily Evolved Animation on WebGL, http://www.intlab.soka.ac.jp/~unemi/sbart/4/DailyWebGL
8. –– : une0ytb – YouTube, http://www.youtube.com/user/une0ytb
9. –– : SBArt4 Home Page, http://www.intlab.soka.ac.jp/~unemi/sbart/4/
Installation: A fully automated evolutionary art. http://www.generativeart.com/GA2012/z-tatsuo.pdf