Efficient target activity detection based on recurrent neural networks

Conference contribution
(Conference Contribution)

Publication Details

Author(s): Gerber D, Meier S, Kellermann W
Publication year: 2017
Pages range: 46-50
Language: English


This paper addresses the problem of Target Activity Detection (TAD) for binaural listening devices. TAD denotes the problem of robustly detecting the activity of a target speaker in a harsh acoustic environment, which comprises interfering speakers and noise (‘cocktail party scenario’). In previous work, it has been shown that employing a Feed-forward Neural Network (FNN) for detecting the target speaker activity is a promising approach to combine the advantage of different TAD features (used as network inputs). In this contribution, we exploit a larger context window for TAD and compare the performance of FNNs and Recurrent Neural Networks (RNNs) with an explicit focus on small network topologies as desirable for embedded acoustic signal processing systems. More specifically, the investigations include a comparison between three different types of RNNs, namely plain RNNs, Long Short-Term Memories, and Gated Recurrent Units. The results indicate that all versions of RNNs outperform FNNs for the task of TAD.

FAU Authors / FAU Editors

Gerber, Daniel
Professur für Nachrichtentechnik
Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik
Meier, Stefan
Professur für Nachrichtentechnik

How to cite

Gerber, D., Meier, S., & Kellermann, W. (2017). Efficient target activity detection based on recurrent neural networks. (pp. 46-50). San Francisco, CA, US.

Gerber, Daniel, Stefan Meier, and Walter Kellermann. "Efficient target activity detection based on recurrent neural networks." Proceedings of the Joint Workshop on Hands-free Speech Communication and Microphone Arrays, San Francisco, CA 2017. 46-50.


Last updated on 2018-19-04 at 04:02