User Tools
**This is an old revision of the document!** ----
====== BrainBeats: Tempo Tracking in EEG Data ====== | Authors | Sebastian Stober, Thomas Prätzlich, Meinard Müller | | Affiliation | University of Western Ontario; International Audio Laboratories Erlangen| | Code | [[https://github.com/github/dmca|Github Link]] | | Dependencies | [[https://github.com/sstober/openmiir| OpenMIIR Dataset (Github)]] | | | [[https://github.com/sstober/deepthought| deepthought project (Github)]] for data export | | | [[http://resources.mpi-inf.mpg.de/MIR/tempogramtoolbox/| Tempogram Toolbox]] | ===== Task ===== Can we track the beat or the tempo of a music piece in brain waves recorded during listening? The OpenMIIR dataset((Sebastian Stober, Avital Sternin, Adrian M. Owen and Jessica A. Grahn: "Towards Music Imagery Information Retrieval: Introducing the OpenMIIR Dataset of EEG Recordings from Music Perception and Imagination." In: Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR’15), 2015. [[ http://ismir2015.uma.es/articles/224_Paper.pdf |Paper]] [[http://bib.sebastianstober.de/ismir2015poster.pdf|Poster]])) comprises EEG recordings((Electroencephalography (EEG) is a popular non-invasive neuroimaging technique that relies on electrodes placed on the scalp to measure the electrical activity of the brain.)) of people listing to 12 short music pieces. {{:brainbeats_wiki_figure_1.png?400|}} We wanted to know whether it is possible to track the tempo in the EEG signal just as this would be done for audio data. {{:brainbeats_wiki_figure_2.png?400|}} The Tempogram Toolbox already does a great job for the music stimuli. {{:brainbeats_wiki_figure_3.png?400|}} Our idea is to apply similar techniques to the EEG data. However, because the EEG is very noisy, we applied some pre-processing. First, we aggregated several EEG channels into one signal. Then, we applied a suitable high-pass filter and normalized the signal by subtracting a kind of moving average curve. {{:brainbeats_wiki_figure_4.png?400|}} The resulting signal is then used as a kind of novelty curve. {{:brainbeats_wiki_figure_5.png?400|}} ===== Example ===== You can write math: $$ x = a^{100} $$ A footnote or reference looks like this((Mastering is the process of applying equalization, compression, reverb, and other nonlinearities to an audio recording to improve it sound.)). You can also include images: {{http://labrosa.ee.columbia.edu/files/labROSA-header.png|}}
