Graph Cepstrum: Spatial Feature Extracted from Partially Connected Microphones
This work addresses the challenge of robust acoustic scene classification for applications using distributed microphone arrays with partial synchronization, representing an incremental improvement over conventional spatial features.
The paper tackles the problem of spatial feature extraction for acoustic scene analysis using partially synchronized or closely located distributed microphones by introducing a graph-based cepstrum that utilizes inverse graph Fourier transform to extract spatial information robustly, with experiments on real environmental sounds showing improved robustness in classifying acoustic scenes, especially when there are large synchronization mismatches between microphone groups.
In this paper, we propose an effective and robust method of spatial feature extraction for acoustic scene analysis utilizing partially synchronized and/or closely located distributed microphones. In the proposed method, a new cepstrum feature utilizing a graph-based basis transformation to extract spatial information from distributed microphones, while taking into account whether any pairs of microphones are synchronized and/or closely located, is introduced. Specifically, in the proposed graph-based cepstrum, the log-amplitude of a multichannel observation is converted to a feature vector utilizing the inverse graph Fourier transform, which is a method of basis transformation of a signal on a graph. Results of experiments using real environmental sounds show that the proposed graph-based cepstrum robustly extracts spatial information with consideration of the microphone connections. Moreover, the results indicate that the proposed method more robustly classifies acoustic scenes than conventional spatial features when the observed sounds have a large synchronization mismatch between partially synchronized microphone groups.