Dictionary Extraction From A Collection Of Spectrograms For Bioacoustics Monitoring
Jose F. Ruiz-Munoz, Zeyu You, Raviv Raich, Xiaoli Z. Fern

Dictionary learning of spectrograms consists of detecting their fundamental spectra-temporal patterns and their associated activation signals. In this paper, we propose an efficient convolutive dictionary learning approach for analyzing repetitive bioacoustics patterns from a collection of audio recordings. Our method is inspired by the convolutive non-negative matrix factorization (CNMF) model. The proposed approach relies on random projection for reduced computational complexity. As a consequence, the non-negativity requirement on the dictionary words is relaxed. Moreover, the proposed approach is well-suited for a collection of discontinuous spectrograms. We evaluate our approach on synthetic examples and on two real datasets consisting of multiple birds audio recordings. Results show that the learned dictionary is formed by the most relevant patterns in each dataset. Additionally, we apply the approach for spectrogram denoising in the presence of rain noise artifacts.