The aim of the study is to transpose and extend to a set of environmental sounds the notion of sound descriptors usually used for musical sounds. Four separate primary studies dealing with interior car sounds, air-conditioning units, car horns, and closing car doors are considered collectively. The corpus formed by these initial stimuli is submitted to new experimental studies and analyses, both for revealing metacategories and for defining more precisely the limits of each of the resulting categories. In a second step, the new structure is modeled: common and specific dimensions within each category are derived from the initial results and new investigations of audio features are performed. Furthermore, an automatic classifier based on two audio descriptors and a multinomial logistic regression procedure is implemented and validated with the corpus.

No abstract

No abstract

The purpose of this study is to propose a scheme of environmental sound description based on the comparison and generalization of 4 timbre studies of diverse environmental sounds. In the medium term, the aim is to make the indexing and classification processes of this kind of sound automatic, which is essential for sound content-based searching and browsing methods using perceptual models of environmental sounds. First, we inventoried the stimuli, experiments and perceptual results of these 4 studies. Then, we experimentally identified 3 main environmental sound categories that constitute this overall sound dataset: impact sounds, motor sounds and instrument-like sounds. We developed an efficient tool that predicts these categories according to only two acoustic features calculated on the signal. However, because of the specificities of the sound production of these three categories, each of them has its own timbre space. Therefore, we finally used perceptually relevant acoustic features to explain these timbre spaces, according to the main acoustic characteristics that define each sound class. We found that timbral brightness is a common feature used to discriminate sounds in all classes, while other particular features are specifically used within each class. [Work partially supported by the SamplerOrchestrator project of the ANR program]

The aim of the study is to transpose and extend to a set of environmental sounds the notion of sound descriptors usually used for musical sounds. Four separate primary studies dealing with interior car sounds, air-conditioning units, car horns, and closing car doors are considered collectively. The corpus formed by these initial stimuli is submitted to new experimental studies and analyses, both for revealing metacategories and for defining more precisely the limits of each of the resulting categories. In a second step, the new structure is modeled: common and specific dimensions within each category are derived from the initial results and new investigations of audio features are performed. Furthermore, an automatic classifier based on two audio descriptors and a multinomial logistic regression procedure is implemented and validated with the corpus.