no code implementations • 2 Nov 2021 • Sebastian Ribecky, Jakob Abeßer, Hanna Lukashevich
To achieve this, we propose a multi-input deep neural network architecture, which simultaneously processes mel-spectrogram, CENS-chromagram and tempogram in order to extract informative features for the different disentangled musical dimensions: genre, mood, instrument, era, tempo, and key.
1 code implementation • 26 Oct 2021 • Jakob Abeßer, Meinard Müller
The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics.
no code implementations • 6 May 2021 • Jakob Abeßer
This paper introduces a novel dataset for polyphonic sound event detection in urban sound monitoring use-cases.
no code implementations • 28 Apr 2021 • Jakob Abeßer, Saichand Gourishetti, András Kátai, Tobias Clauß, Prachi Sharma, Judith Liebetrau
In many urban areas, traffic load and noise pollution are constantly increasing.
no code implementations • 17 Feb 2021 • David S. Johnson, Wolfgang Lorenz, Michael Taenzer, Stylianos Mimilakis, Sascha Grollmisch, Jakob Abeßer, Hanna Lukashevich
Research on sound event detection (SED) in environmental settings has seen increased attention in recent years.
no code implementations • 15 Sep 2020 • Alexandra Draghici, Jakob Abeßer, Hanna Lukashevich
In this paper, we investigate a previously proposed algorithm for spoken language identification based on convolutional neural networks and convolutional recurrent neural networks.