Processing apparatus, processing method, learning apparatus, and computer program product

A processing method that is executed by an information processing apparatus, the processing method comprising:

• cutting out, from an input signal, a plurality of partial signals that are predetermined parts in the input signal;
• in a plurality of pieces of partial processing corresponding to the partial signals one-to-one, executing processing on corresponding partial signals using a plurality of respective neural networks having the same layer structure with each other to generate a plurality of intermediate signals including a plurality of signals corresponding to a plurality of channels;
• executing predetermined statistical processing on signals for each of the plurality of channels for each of the plurality of intermediate signals corresponding to the plurality of partial signals, to calculate statistics for each channel and generate a concatenated signal by concatenating the statistics of the plurality of respective intermediate signals for each channel;
• generating a synthetic signal by performing predetermined processing on the concatenated signal;
• and
• outputting an output signal in accordance with the synthetic signal.

A non-transitory computer program product comprising a computer-readable medium including programmed instructions, the instructions causing a computer to function as:

• a cutout portion configured to cut out, from an input signal, a plurality of partial signals that are predetermined parts in the input signal;
• a plurality of part processors corresponding to the partial signals one-to-one and configured to execute processing on the plurality of partial signals using a pluraltiy of respective neural networks having the same layer structure with each other to generate a plurality of intermediate signals including a plurality of signals corresponding to a plurality of channels;
• a concatenation portion configured to execute predetermined statistical processing on signals for each of the plurality of channels for each of the plurality of intermediate signals corresponding to the plurality of partial signals, to calculate statistics for each channel and generate a concatenated signal by concatenating the statistics of the plurality of respective intermediate signals for each channel;
• a synthesizing portion configured to generate a synthetic signal by performing predetermined processing on the concatenated signal;
• and
• a signal output portion configured to output an output signal in accordance with the synthetic signal.