{"department":[{"_id":"54"}],"title":"Benchmarking Neural Network Architectures for Acoustic Sensor Networks","_id":"11836","related_material":{"link":[{"relation":"supplementary_material","url":"https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Ebbers_Poster.pdf","description":"Poster"}]},"citation":{"chicago":"Ebbers, Janek, Jens Heitkaemper, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Benchmarking Neural Network Architectures for Acoustic Sensor Networks.” In <i>ITG 2018, Oldenburg, Germany</i>, 2018.","short":"J. Ebbers, J. Heitkaemper, J. Schmalenstroeer, R. Haeb-Umbach, in: ITG 2018, Oldenburg, Germany, 2018.","bibtex":"@inproceedings{Ebbers_Heitkaemper_Schmalenstroeer_Haeb-Umbach_2018, title={Benchmarking Neural Network Architectures for Acoustic Sensor Networks}, booktitle={ITG 2018, Oldenburg, Germany}, author={Ebbers, Janek and Heitkaemper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2018} }","apa":"Ebbers, J., Heitkaemper, J., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2018). Benchmarking Neural Network Architectures for Acoustic Sensor Networks. <i>ITG 2018, Oldenburg, Germany</i>.","ieee":"J. Ebbers, J. Heitkaemper, J. Schmalenstroeer, and R. Haeb-Umbach, “Benchmarking Neural Network Architectures for Acoustic Sensor Networks,” 2018.","mla":"Ebbers, Janek, et al. “Benchmarking Neural Network Architectures for Acoustic Sensor Networks.” <i>ITG 2018, Oldenburg, Germany</i>, 2018.","ama":"Ebbers J, Heitkaemper J, Schmalenstroeer J, Haeb-Umbach R. Benchmarking Neural Network Architectures for Acoustic Sensor Networks. In: <i>ITG 2018, Oldenburg, Germany</i>. ; 2018."},"user_id":"460","date_created":"2019-07-12T05:29:11Z","status":"public","year":"2018","quality_controlled":"1","oa":"1","author":[{"full_name":"Ebbers, Janek","id":"34851","last_name":"Ebbers","first_name":"Janek"},{"first_name":"Jens","full_name":"Heitkaemper, Jens","id":"27643","last_name":"Heitkaemper"},{"full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer","first_name":"Joerg"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","id":"242","first_name":"Reinhold"}],"abstract":[{"lang":"eng","text":"Due to their distributed nature wireless acoustic sensor networks offer great potential for improved signal acquisition, processing and classification for applications such as monitoring and surveillance, home automation, or hands-free telecommunication. To reduce the communication demand with a central server and to raise the privacy level it is desirable to perform processing at node level. The limited processing and memory capabilities on a sensor node, however, stand in contrast to the compute and memory intensive deep learning algorithms used in modern speech and audio processing. In this work, we perform benchmarking of commonly used convolutional and recurrent neural network architectures on a Raspberry Pi based acoustic sensor node. We show that it is possible to run medium-sized neural network topologies used for speech enhancement and speech recognition in real time. For acoustic event recognition, where predictions in a lower temporal resolution are sufficient, it is even possible to run current state-of-the-art deep convolutional models with a real-time-factor of 0:11."}],"publication":"ITG 2018, Oldenburg, Germany","date_updated":"2023-10-26T08:12:40Z","type":"conference","language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Ebbers_Paper.pdf"}]}