Learning method based on multi-channel cross-tower network for jointly suppressing acoustic echo and background noise

A multi-channel based noise and echo signal integrated cancellation device using deep neural network comprising:

• a plurality of microphone encoders that receive a plurality of microphone input signals including an echo signal, and a speaker's voice signal, convert the plurality of microphone input signals into a plurality of pieces of conversion information, and output the converted plurality of pieces of conversion information;
• a channel convert unit for compressing the plurality of pieces of conversion information and converting the plurality of pieces of conversion information into first input information having a size of a single channel and outputting the converted first input information;
• a far-end signal encoder that receives a far-end signal, converts the far-end signal into second input information, and outputs the converted second input information;
• a pre-learned second artificial neural network configured to use third input information, which is a sum of the first input information and the second input information, as input information, and output an estimated echo signal obtained by estimating the echo signal from the second input information as output information;
• a pre-learned third artificial neural network configured to use the third input information as input information and output an estimated noise signal obtained by estimating a noise signal from the second input information as output information;
• and
• a voice signal estimator configured to output an estimated voice signal obtained by estimating voice information based on the estimated echo signal, the estimated noise signal, and the second input information,
• wherein the pre-learned second artificial neural network includes a 2-A artificial neural network and a 2-B artificial neural network connected in series, and the pre-learned third artificial neural network includes a 3-A artificial neural network and a 3-B artificial neural network connected in series,
• wherein the 2-B artificial neural network uses fourth input information obtained by subtracting third output information output from the 3-A artificial neural network from the third input information, and based on the fourth input information, uses fourth output information including information obtained by estimating the echo signal as output information, and
• wherein the 3-B artificial neural network uses fifth input information obtained by subtracting second output information output from the 2-A artificial neural network from the third input information, and based on the fifth input information, uses fifth output information including information estimating the noise signal as output information.