8–12 Sept 2026
Europe/Vienna timezone

Can Algorithms Be Illuded? Machine Learning and the Speech-to- Song Illusion

FA2026/623
9 Sept 2026, 09:40
20m
Saal 5 (Messe Congress Graz)

Saal 5

Messe Congress Graz

A20 Speech A20.00 Speech

Speaker

Robert Gogol (Adam Mickiewicz University in Poznan)

Description

This study explores the 'Speech-to-Song Illusion' discovered by Diana Deutsch. Specifically, it questions whether a correlation can be established between subjective human perception of the illusion and objective analyses performed by machine learning tools within the open-source Essentia library and others. To identify and examine the specific region, where machine learning algorithms yield ambiguous classifications (speech - song) for speech recordings, this study utilizes the spectro-temporal degradation techniques developed by Philippe Albouy in 2023. Can the model’s predictions for the same speech recordings, evaluated by human listeners, be correlated with the results of a subjective experiment examining their ability to evoke the speech-to-song illusion?

Authors

Robert Gogol (Adam Mickiewicz University in Poznan) Anna Preis (Adam Mickiewicz University in Poznan) Jan Felcyn (Adam Mickiewicz University in Poznan)

Presentation materials

There are no materials yet.