Towards a device for helping deaf people to dance: estimation of forro bar length using artificial neural network

Dance has the potential to improve people's quality of life, as well as assist to decrease depression and anxiety. However, the lack of technologies capable of exploring alternative senses of hearing limits music and dance's beneficial effects on listeners. In order to find a model capable of being implemented in accessible devices, this work evaluated the use of a model based on neural networks to estimate the forro music bar length. Model variations were trained for seven datasets composed of mixes of music samples without noise, with real noise and with white noise. For each dataset, the best variation was selected and these were evaluated for the same real noise samples. The model variations that were presented to samples with real noise in the training estimated the bar duration with an average percentage error of less than 7% in the test step, being significantly better the model trained only with real sample. The evaluated model was able to estimate the length of the forro music bar length, even in real scenarios, as long as it was presented in this scenario during training. Increased database diversity and the use of data augmentation techniques can lead to improvements in the generalizability of the model. The simplicity of the evaluated model and its ability to learn when properly trained, indicate its potential to be used, in real time, on a mobile device to pass the rhythm of forro music to deaf and hard of hearing (D/HH) people.