Sample drop detection for asynchronous devices distributed in space

European Signal Processing Conference (EUSIPCO), pp. 815–819

Abstract

In many applications of multi-microphone multi-device processing, the synchronization among different input channels can be affected by the lack of a common clock and isolated drops of samples. In this work, we address the issue of sample drop detection in the context of a conversational speech scenario, recorded by a set of microphones distributed in space. The goal is to design a neural-based model that given a short window in the time domain, detects whether one or more devices have been subjected to a sample drop event. The candidate time windows are selected from a set of large time intervals, possibly including a sample drop, and by using a preprocessing step. The latter is based on the application of normalized cross-correlation between signals acquired by different devices. The architecture of the neural network relies on a CNN-LSTM encoder, followed by multi-head attention. The experiments are conducted using both artificial and real data. Our proposed approach obtained F1 score of 88% on an evaluation set extracted from the CHiME-5 corpus. A comparable performance was found in a larger set of experiments conducted on a set of multi-channel artificial scenes.

Authors 3

1. Tina Raissi Aachen Human Language Technology and Pattern Recognition

   RWTH Aachen University

   Affiliation as printed

   Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany

2. Santiago Pascual

   Universitat Politècnica de Catalunya

   Affiliation as printed

   Santiago Pascual is currently at Dolby Laboratories, Barcelona, Spain

   Universitat Politècnica de Catalunya, Barcelona, Spain

3. Maurizio Omologo

   Fondazione Bruno Kessler · FBK Center for Information and Communication Technology

   Affiliation as printed

   Center for Information and Communication Technology (ICT), Fondazione Bruno Kessler (FBK), Trento, Italy