Neural network and DSP based decoder for DTMF signals

A novel approach for the efficient digital decoding of DTMF signals used in telecommunications is based on an artificial neural network (ANN) implemented on a digital signal processor (DSP). After the appropriate training phase the ANN is able to associate a digital output corresponding to the received DTMF signal. The proposed approach may allow the possibility of implementing a real-time non-intrusive decoder. This decoder is fully described and particular attention paid to the solutions adopted for optimising the ANN's computation on the DSP. A comparison is made of the performance obtained by the proposed approach, and that recommended by the CCITT standard. Finally, experimental results are given which highlight the performance of the apparatus in different real conditions in DTMF signal decoding.