On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-varying Sampling Rate Offsets and Speaker Changes

TL;DR

This paper introduces a model and estimation algorithm for synchronizing wireless acoustic sensor networks with time-varying sampling rate offsets and speaker movements, utilizing deep neural networks for distance estimation.

Contribution

It presents a novel sampling rate offset model for dynamic conditions and combines it with deep learning-based distance estimates for improved synchronization.

Findings

Effective handling of time-varying sampling rate offsets.

Successful integration of neural network distance estimates.

Enhanced synchronization accuracy in dynamic environments.

Abstract

A wireless acoustic sensor network records audio signals with sampling time and sampling rate offsets between the audio streams, if the analog-digital converters (ADCs) of the network devices are not synchronized. Here, we introduce a new sampling rate offset model to simulate time-varying sampling frequencies caused, for example, by temperature changes of ADC crystal oscillators, and propose an estimation algorithm to handle this dynamic aspect in combination with changing acoustic source positions. Furthermore, we show how deep neural network based estimates of the distances between microphones and human speakers can be used to determine the sampling time offsets. This enables a synchronization of the audio streams to reflect the physical time differences of flight.