Data Science Chair

    Our paper "Detecting Presence Of Speech In Acoustic Data Obtained From Beehives" got accepted @ DCASE21


    Our workshop paper "Detecting Presence Of Speech In Acoustic Data Obtained From Beehives" got accepted at the DCASE21 (Workshop on Detection and Classification of Acoustic Scenes and Events) and will be presented in November this year

    In this work we analyze the application of Siamese Nerual Networks for distinguishing two types of audio samples obtained from beehives: those containing human speech and those without.


    Sound recorded from beehives is important to understand a colony’s state. This fact is used in the we4bee1 project, where beehives are equipped with sensors (among them microphones), distributed to educational institutions and set up to record colony characteristics at the communication level. Due to data protection laws, we have to ensure that no human is recorded besides the bees’ sound. However, detecting the presence of speech is challenging since the frequencies of human speech and the humming of bees largely overlap.
    Despite having access to only a limited amount of labeled data, in this initial study we show how to solve this problem using Siamese networks. We find that using common convolutional neural networks in a Siamese setting can strongly improve the ability to detect human speech in recordings obtained from beehives. By adding train-time augmentation techniques, we are able to reach a recall of up to 100 %, resulting in a reliable technique adhering to privacy regulations. Our results are useful for research projects that require written permits for acquiring data, which impedes the collection of samples. Further, all steps, including pre-processing, are calculated on the GPU, and can be used in an end-to-end pipeline, which allows for quick prototyping.