FIG. 13A is a block diagram illustrating an unsupervised learning module 1300 used to train a neural network 1310 in compressing an audio input to a sequence of haptic cues, according to an embodiment. The unsupervised learning module 1300 may be used to generate a set of coefficients and other settings for the neural network 1310. In one embodiment, the neural network 1310 is also known as a machine learning circuit or a machine learning algorithm. The components of the block diagram in FIG. 13A may be stored as computer readable instructions in memory, such as the memory 813. In another embodiment, these components are separately implemented using dedicated hardware, including a processor and memory.
The unsupervised learning module 1300 receives an acoustic signal 1302 as input. The input may be any audio waveform, and may be encoded in any format, at any bit rate, sample rate, etc.
