J. D. Ziegler, A. Koch, and A. Schilling, “Speech Classification for Acoustic Source Localization and Tracking Applications Using Convolutional Neural Networks,” in Proc. AES Convention 145, Oct. 2018, pp. 10101:1-9. [Online]. Available: https://aes.org/publications/elibrary-page/?id=19827
Ziegler JD, Koch A, Schilling A. Speech Classification for Acoustic Source Localization and Tracking Applications Using Convolutional Neural Networks. In: AES Convention 145. Audio Engineering Society; 2018.pp. 10101:1-9. Available from: https://aes.org/publications/elibrary-page/?id=19827
@inproceedings{Ziegler2018_19827,
author = {Ziegler, Jonathan D. and Koch, Andreas and Schilling, Andreas},
title = {{Speech Classification for Acoustic Source Localization and Tracking Applications Using Convolutional Neural Networks}},
booktitle = {AES Convention 145},
pages = {10101:1-9},
url = {https://aes.org/publications/elibrary-page/?id=19827},
year = {2018},
month = oct,
publisher = {Audio Engineering Society},
address = {New York}
}
TY - CPAPER
TI - Speech Classification for Acoustic Source Localization and Tracking Applications Using Convolutional Neural Networks
AU - Ziegler, Jonathan D.
AU - Koch, Andreas
AU - Schilling, Andreas
T2 - AES Convention 145
SP - 1
EP - 9
M1 - Paper 10101
PY - 2018
DA - 2018/10/06
UR - https://aes.org/publications/elibrary-page/?id=19827
PB - Audio Engineering Society
CY - New York
LA - en
AB - Acoustic Source Localization and Speaker Tracking are continuously gaining importance in fields such as human computer interaction, hands-free operation of smart home devices, and telecommunication. A set-up using a Steered Response Power approach in combination with high-end professional microphone capsules is described and the initial processing stages for detection angle stabilization are outlined. The resulting localization and tracking can be improved in terms of reactivity and angular stability by introducing a Convolutional Neural Network for signal/noise discrimination tuned to speech detection. Training data augmentation and network architecture are discussed; classification accuracy and the resulting performance boost of the entire system are analyzed.
ER -