Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networks

We present an approach to deep neural network based (DNN-based) distance estimation in reverberant rooms for supporting geometry calibration tasks in wireless acoustic sensor networks. Signal diffuseness information from acoustic signals is aggregated via the coherent-to-diffuse power ratio to obtain a distance-related feature, which is mapped to a source-to-microphone distance estimate by means of a DNN. This information is then combined with direction-of-arrival estimates from compact microphone arrays to infer the geometry of the sensor network. Unlike many other approaches to geometry calibration, the proposed scheme does only require that the sampling clocks of the sensor nodes are roughly synchronized. In simulations we show that the proposed DNN-based distance estimator generalizes to unseen acoustic environments and that precise estimates of the sensor node positions are obtained.

[1]  Reinhold Häb-Umbach,et al.  Acoustic Microphone Geometry Calibration: An overview and experimental evaluation of state-of-the-art algorithms , 2016, IEEE Signal Processing Magazine.

[2]  Walter Kellermann,et al.  Acoustic Source Position Estimation Based On Multi-Feature Gaussian Processes , 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

[3]  Li Zhang,et al.  Lagrange Programming Neural Network for TOA-Based Localization with Clock Asynchronization and Sensor Location Uncertainties , 2018, Sensors.

[4]  Reinhold Häb-Umbach,et al.  Microphone Array Position Self-Calibration from Reverberant Speech Input , 2012, IWAENC.

[5]  Alexander Bertrand,et al.  Applications and trends in wireless acoustic sensor networks: A signal processing perspective , 2011, 2011 18th IEEE Symposium on Communications and Vehicular Technology in the Benelux (SCVT).

[6]  Aleksei Romanenko,et al.  R-Vectors: New Technique for Adaptation to Room Acoustics , 2019, INTERSPEECH.

[7]  Reinhold Häb-Umbach,et al.  DOA-estimation based on a complex Watson kernel method , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[8]  Walter Kellermann,et al.  Distributed Source Localization in Acoustic Sensor Networks Using the Coherent-to-Diffuse Power Ratio , 2019, IEEE Journal of Selected Topics in Signal Processing.

[9]  Reinhold Häb-Umbach,et al.  MARVELO - A Framework for Signal Processing in Wireless Acoustic Sensor Networks , 2018, ITG Symposium on Speech Communication.

[10]  Andreas BRENDEL,et al.  Probabilistic modeling for learning-based distance estimation , 2019 .

[11]  Reinhold Haeb-Umbach,et al.  Audio-Visual Data Processing for Ambient Communication , 2009 .

[12]  Fucheng Guo,et al.  Direct Position Determination in Asynchronous Sensor Networks , 2019, IEEE Transactions on Vehicular Technology.

[13]  Jonathan G. Fiscus,et al.  Darpa Timit Acoustic-Phonetic Continuous Speech Corpus CD-ROM {TIMIT} | NIST , 1993 .

[14]  Lukás Burget,et al.  Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge , 2018, ArXiv.

[15]  Reinhold Häb-Umbach,et al.  Unsupervised Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences , 2011, INTERSPEECH.

[16]  Walter Kellermann,et al.  Unbiased coherent-to-diffuse ratio estimation for dereverberation , 2014, 2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC).

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Jont B. Allen,et al.  Image method for efficiently simulating small‐room acoustics , 1976 .