works
bio
contact
Instagram mail


YOU’RE KINDA is a provocative mirror of your personal level of state rule regime.

Hearing human speech, it classifies it under the relevant regime, which is determined by the color. Classification is based on The Democracy Index compiled by the Economist Intelligence Unit (EIU). Its intention is to measure the state of democracy in 167 countries. The index categorizes each country in one of four regime types: full democracies (green), flawed democracies (blue), hybrid regimes (yellow) and authoritarian regimes (red).

The program complex was previously trained with recorded speeches of state leaders (presidents, prime ministers, queens, and kings) from all over the world. To minimize the difference in the temper and the mood all recorded speeches were Christmas and New Year greetings to the nation. All the speeches were divided into four groups according to the Democracy Index. By getting the input data the program matches it against the trained speeches held in the database, returning the result that it matches.

The framework used in the installation is the library which can memorize audio by listening to it once and fingerprinting it. The "fingerprints" are locality sensitive hashes that are computed from the spectrogram of the audio. This is done by taking the fast Fourier transformation (FFT) of the signal over overlapping windows of the record and identifying peaks.













works  /  you're kinda  bio  contact  mail  instagram 
YOU’RE KINDA is a provocative mirror of your personal level of state rule regime.

Hearing human speech, it classifies it under the relevant regime, which is determined by the color. Classification is based on The Democracy Index compiled by the Economist Intelligence Unit (EIU). Its intention is to measure the state of democracy in 167 countries. The index categorizes each country in one of four regime types: full democracies (green), flawed democracies (blue), hybrid regimes (yellow) and authoritarian regimes (red).

The program complex was previously trained with recorded speeches of state leaders (presidents, prime ministers, queens, and kings) from all over the world. To minimize the difference in the temper and the mood all recorded speeches were Christmas and New Year greetings to the nation. All the speeches were divided into four groups according to the Democracy Index. By getting the input data the program matches it against the trained speeches held in the database, returning the result that it matches.

The framework used in the installation is the library which can memorize audio by listening to it once and fingerprinting it. The "fingerprints" are locality sensitive hashes that are computed from the spectrogram of the audio. This is done by taking the fast Fourier transformation (FFT) of the signal over overlapping windows of the record and identifying peaks.