Estimation of the road traffic sound levels based on Non-Negative Matrix Factorization dataset

<p>Sound database to compute the NonnegMatrixFact experience (download the .m files here: https://github.com/jean-remyGloaguen/article2017EstimationAmbiance) dedicated to the estimation of the traffic sound level on urban sound mixtures.</p> <p>This sound database includes two subfolders: <em>ambiance</em> and <em>dictionary</em></p> <p><em>- ambiance </em>folder includes 6&nbsp; sub-corpus (<em>alert</em>, <em>animals, climate, human, mechanics</em> and <em>transportation</em>). In each sub-corpus, 50 sound mixtures are available and divided into two files: one dedicated to the traffic signal, the other to the interfering signal.</p> <p><em>- dictionary </em>folder includes the isolated sounds dedicated to the dictionary learning for NMF</p>