Robust intrusive perceptual audio quality assessment based on convolutional neural networks

A computer-implemented deep-learning-based system for determining an indication of an audio quality of an input audio frame, the system comprising:

• at least one inception block configured to receive at least one representation of an input audio frame and to map the at least one representation of the input audio frame into a feature map, wherein the input audio frame is derived from a stereo audio signal comprising a left channel and a right channel, and wherein the at least one representation of the input audio frame comprises for each of a middle channel, a side channel, a left channel and a right channel a representation of a clean reference input audio frame and a representation of a degraded input audio frame, the middle and side channel corresponding to a sum and a difference of the left and right channels, and wherein the at least one inception block is initialized using one or more weight coefficients associated with a trained model used to process mono audio signals;
• and
• at least one fully connected layer configured to receive a feature map corresponding to the at least one representation of the input audio frame from the at least one inception block, wherein the at least one fully connected layer is configured to determine the indication of the audio quality of the input audio frame;
• wherein the at least one inception block comprises:
• a plurality of parallel paths of convolutional layers, wherein at least one parallel path includes a convolutional layer with an m×n sized kernel, wherein the integer m is different from the integer n.

A method of operating a computer-implemented deep-learning-based system for determining an indication of an audio quality of an input audio frame of a stereo audio signal, wherein the system comprises at least one inception block and at least one fully connected layer, the method including the steps of:

• transferring one or more weight coefficients from an inception block associated with determining audio quality of a mono audio signal to the at least one inception block to initialize the at least one inception block for processing of stereo audio signals;
• receiving, by the at least one inception block, at least one representation of the input audio frame comprising for each of a middle channel, a side channel, a left channel and a right channel a representation of a clean reference input audio frame and a representation of a degraded input audio frame, the middle and side channel corresponding to a sum and a difference of the left and right channels;
• mapping, by the at least one inception block, the at least one representation of the input audio frame into feature maps;
• and
• predicting, by the at least one fully connected layer, the indication of the audio quality of the input audio frame based on the feature maps.