13. Februar 2019

14.30 o'clock,
Seminar Room, Wohllebengasse 12-14 / Ground Floor 

The problem of low inter-rater agreement in annotating music - Arthur Flexer

In applying machine learning to musical audio signals, the general goal is to learn a mapping from an input (e.g. a song) to an output (e.g. an annotation such as genre). Since the human perception of music and its annotation is highly subjective with low inter-rater agreement, the validity of such machine learning experiments is unclear. Because it is not meaningful to have computational models that go beyond the level of human agreement, these levels of inter-rater agreement present a natural upper bound for any algorithmic approach. We illustrate this fundamental evaluation problem using results from modeling music similarity between pieces of music, as utilized in automatic music recommendation.

 

Upcoming Events

ARI-Guest-Talk: Operator representation of frames with a focus on Gabor frames

27. Februar 2019

14.30 o'clock,
Seminar Room, Wohllebengasse 12-14 / Ground Floor 

Read more ...
 

ARI-Guest-Talk: PIP-space valued reproducing pairs of measurable functions

06. March 2019

14.30 o'clock,
Seminar Room, Wohllebengasse 12-14 / Ground Floor 

Read more ...
 

Internationaler Tag gegen Lärm 2019

22. Internationaler Tag gegen Lärm

am 24. April 2019, 9:30 - 17:30 Uhr

Am Aktionstag des ÖAW-Instituts für Schallforschung laden
auch heuer zahlreiche Stationen Erwachsene und Kinder zum Mitmachen ein.

 Internationaler Tag gegen Lärm 2019
© Österr. Galerie Belvedere (Büste)
Read more ...
 

SSW10

SSW10 - The 10th
ISCA Speech Synthesis Workshop

20. - 22. September 2019

Vienna, Austria

 

News