Sound Representation and Classification Benchmark for Domestic Robots
This work addresses sound classification challenges for domestic robots, but it is incremental as it focuses on benchmarking existing methods on a new dataset.
The authors tackled the problem of sound representation and classification for domestic robots by creating a dataset recorded in realistic conditions with the NAO robot and conducting a benchmark to evaluate various methods based on classification scores, computation times, and memory requirements.
We address the problem of sound representation and classification and present results of a comparative study in the context of a domestic robotic scenario. A dataset of sounds was recorded in realistic conditions (background noise, presence of several sound sources, reverberations, etc.) using the humanoid robot NAO. An extended benchmark is carried out to test a variety of representations combined with several classifiers. We provide results obtained with the annotated dataset and we assess the methods quantitatively on the basis of their classification scores, computation times and memory requirements. The annotated dataset is publicly available at https://team.inria.fr/perception/nard/.