no code implementations • 28 Feb 2023 • Irene Martín-Morató, Manu Harju, Paul Ahokas, Annamaria Mesaros
In this paper, we study the use of soft labels to train a system for sound event detection (SED).
no code implementations • 8 Jun 2022 • Irene Martín-Morató, Francesco Paissan, Alberto Ancilotto, Toni Heittola, Annamaria Mesaros, Elisabetta Farella, Alessio Brutti, Tuomas Virtanen
The provided baseline system is a convolutional neural network which employs post-training quantization of parameters, resulting in 46. 5 K parameters, and 29. 23 million multiply-and-accumulate operations (MMACs).
no code implementations • 26 Jul 2021 • Irene Martín-Morató, Manu Harju, Annamaria Mesaros
Strong labels are a necessity for evaluation of sound event detection methods, but often scarcely available due to the high resources required by the annotation task.
1 code implementation • 28 May 2021 • Irene Martín-Morató, Toni Heittola, Annamaria Mesaros, Tuomas Virtanen
The most used techniques among the submissions were residual networks and weight quantization, with the top systems reaching over 70% accuracy, and log loss under 0. 8.