ABSTRACT
It is very challenging to evaluate the creative work of artificial intelligence, such as algorithmic composition. Due to the nature of creativity, most existing criteria of music analysis, for example, similarity of the data, cannot be used directly to measure the quality of a new piece of music composed by computer. Subjective evaluation based on questionnaire lacks quantitative evaluation with solid evidence. To address these difficulties, this paper proposes a novel computational model combined with a novel psychological paradigm. Utilizing brain imaging techniques, the proposed evaluation method can provide reliable musicality score for machine-composed music.
- Eckart O Altenmüller. 2001. How many music centers are in the brain? Annals of the New York Academy of Sciences Vol. 930, 1 (2001), 273--280.Google ScholarCross Ref
- Eckart O Altenmüller, Kristian Schürmann, Vanessa K Lim, and Dietrich Parlitz. 2002. Hits to the left, flops to the right: different emotions during listening to music are reflected in cortical lateralisation patterns. Neuropsychologia, Vol. 40, 13 (2002), 2242--2256.Google ScholarCross Ref
- Paulo Estév ao Andrade and Joydeep Bhattacharya. 2003. Brain tuned to music. Journal of the Royal Society of Medicine Vol. 96, 6 (2003), 284--287.Google ScholarCross Ref
- Marc Bangert and Eckart O Altenmüller. 2003. Mapping perception to action in piano practice: a longitudinal DC-EEG study. BMC neuroscience, Vol. 4, 1 (2003), 26.Google Scholar
- Thomas G Bever and Robert J Chiarello. 1974. Cerebral dominance in musicians and nonmusicians. Science, Vol. 185, 4150 (1974), 537--539.Google Scholar
- Joydeep Bhattacharya and Hellmuth Petsche. 2001. Universality in the brain while listening to music. Proceedings of the Royal Society of London B: Biological Sciences, Vol. 268, 1484 (2001), 2423--2433.Google ScholarCross Ref
- Joydeep Bhattacharya, Hellmuth Petsche, and Ernesto Pereda. 2001. Long-range synchrony in the γ band: role in music perception. Journal of Neuroscience Vol. 21, 16 (2001) 6329--6337.Google ScholarCross Ref
- Zhijie Bian, Qiuli Li, Lei Wang, Chengbiao Lu, Shimin Yin, and Xiaoli Li. 2014. Relative power and coherence of EEG series are related to amnestic mild cognitive impairment in diabetes. Frontiers in aging neuroscience Vol. 6 (2014), 11.Google Scholar
- Hang Chu, Raquel Urtasun, and Sanja Fidler. 2017. Song From PI: A Musically Plausible Network for Pop Music Generation workshop on International Conference on Learning Representations, 2017. ICLR workshop 2017.Google Scholar
- Darrell Conklin. 2016. Chord sequence generation with semiotic patterns. Journal of Mathematics and Music Vol. 10, 2 (2016), 92--106.Google ScholarCross Ref
- David Cope. 1987. Experiments in Musical Intelligence. http://artsites.ucsc.edu/faculty/cope/experiments.htm. (1987).Google Scholar
- David Cope. 1992. Computer modeling of musical intelligence in EMI. Computer Music Journal Vol. 16, 2 (1992), 69--83.Google ScholarCross Ref
- Cheryl L Dickter and Paul D Kieffaber. 2013. EEG methods for the psychological sciences. Sage.Google Scholar
- Isabelle Guyon and André Elisseeff. 2003. An introduction to variable and feature selection. Journal of Machine Learning Research Vol. 3, Mar (2003), 1157--1182. Google ScholarDigital Library
- Norbert Jauvsovec and Katarina Habe. 2003. The "Mozart effect": an electroencephalographic analysis employing the methods of induced event-related desynchronization/synchronization and event-related coherence. Brain Topography, Vol. 16, 2 (2003), 73--84.Google ScholarCross Ref
- Stefan Lattner, Maarten Grachten, and Gerhard Widmer. 2016. Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints. arXiv preprint arXiv:1612.04742 (2016).Google Scholar
- Mu Li and Bao-Liang Lu. 2009. Emotion classification based on gamma-band EEG. In Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. IEEE, 1223--1226.Google Scholar
- Yuan-Pin Lin, Chi-Hong Wang, Tzyy-Ping Jung, Tien-Lin Wu, Shyh-Kang Jeng, Jeng-Ren Duann, and Jyh-Horng Chen. 2010. EEG-based emotion recognition in music listening. IEEE Transactions on Biomedical Engineering, Vol. 57, 7 (2010), 1798--1806.Google ScholarCross Ref
- Sidi Liu, Jinglei Lv, Yimin Hou, Ting Shoemaker, Qinglin Dong, Kaiming Li, and Tianming Liu. 2016. What Makes a Good Movie Trailer?: Interpretation from Simultaneous EEG and Eyetracker Recording Proceedings of the 24th ACM international conference on Multimedia. ACM, 82--86. Google ScholarDigital Library
- Yang Liu, Yan Liu, Yu Zhao, and Kien A Hua. 2015. What strikes the strings of your heart?--Feature mining for music emotion analysis. IEEE Transactions on Affective Computing Vol. 6, 3 (2015), 247--260.Google ScholarDigital Library
- George A Miller. 1995. WordNet: a lexical database for English. Commun. ACM Vol. 38, 11 (1995), 39--41. Google ScholarDigital Library
- Eva Mohedano, Graham Healy, Kevin McGuinness, Xavier Giró-i Nieto, Noel E O'Connor, and Alan F Smeaton. 2014. Object segmentation in images using eeg signals. Proceedings of the 22nd ACM international conference on Multimedia. ACM, 417--426. Google ScholarDigital Library
- Seong-Eun Moon and Jong-Seok Lee. 2015. EEG Connectivity Analysis in Perception of Tone-mapped High Dynamic Range Videos Proceedings of the 23rd ACM international conference on Multimedia. ACM, 987--990. Google ScholarDigital Library
- Yuma Sasaka, Takahiro Ogawa, and Miki Haseyama. 2016. Multimodal Interest Level Estimation via Variational Bayesian Mixture of Robust CCA Proceedings of the 24th ACM international conference on Multimedia. ACM, 387--391. Google ScholarDigital Library
- Erwin-Josef Speckmann. 1993. Introduction of the neurophysiological basis of the EEG and DC potentials. Electroencephalography: Basic principles, clinical applications, and related fields (1993), 15--26.Google Scholar
- Sebastian Stober, Daniel J Cameron, and Jessica A Grahn. 2014. Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings. In Advances in neural information processing systems. 1449--1457. Google ScholarDigital Library
- Sébastien Tremblay, William J MacKen, and Dylan M Jones. 2001. The impact of broadband noise on serial memory: Changes in band-pass frequency increase disruption. Memory, Vol. 9, 4--6 (2001), 323--331.Google ScholarCross Ref
- Andries Van Der Merwe and Walter Schulze. 2011. Music generation with Markov models. IEEE MultiMedia, Vol. 18, 3 (2011), 78--85. Google ScholarDigital Library
- Elliot Waite, Douglas Eck, Adam Roberts, and Dan Abolafia. 2016. Project Magenta. https://magenta.tensorflow.org/. (2016).Google Scholar
- John R Zhang, Jason Sherwin, Jacek Dmochowski, Paul Sajda, and John R Kender. 2014. Correlating Speaker Gestures in Political Debates with Audience Engagement Measured via EEG Proceedings of the 22nd ACM international conference on Multimedia. ACM, 387--396. Google ScholarDigital Library
- Who Composes the Music?: Musicality Evaluation for Algorithmic Composition via Electroencephalography
Recommendations
Armin: Automatic Trance Music Composition using Answer Set Programming
Latin American Workshop on Logic Languages, Algorithms and New Methods of Reasoning (LANMR)The Artificial Intelligence (AI) has taken a leading role in many activities which used to be made “by hand”; one of them is the musical composition. Such task now has another alternative implementation, through the support of software that can compose ...
Automatic music composition using answer set programming
Music composition used to be a pen and paper activity. These days music is often composed with the aid of computer software, even to the point where the computer composes parts of the score autonomously. The composition of most styles of music is ...
AAM: a dataset of Artificial Audio Multitracks for diverse music information retrieval tasks
AbstractWe present a new dataset of 3000 artificial music tracks with rich annotations based on real instrument samples and generated by algorithmic composition with respect to music theory. Our collection provides ground truth onset information and has ...
Comments