Neural Networks for Real-Time Digital Emulation of Guitar Speaker Cabinet Impulse Response

This This paper presents a real-time signal processing system in which a neural network generates the impulse response (IR) of a Marshall 1960A guitar cabinet with 25W Celestion speakers based on user-specified parameters. The parameters include the microphone type, position of the speaker on which the microphone is mounted, distance between the microphone and the cabinet, and off-axis tilting angle. The trained model of neural network can generate the impulse response for a speaker cabinet, as well as the sound of settings not included in training set. Cross-correlation, error-to-signal ratio, power spectral density error, and magnitude-squared coherence were all utilized to assess the model's output. Mean Opinion Score listening tests were performed to determine the similarity of the convolved guitar signals. According to the results, the emulated cabinet sounds were perceived to be nearly identical to the original sounds. The performance of the real-time audio plugin implementation is proved to be computationally efficient. Because raw IR data for each microphone configuration does not need to be saved directly to the PC's memory, utilizing it in music production work can be more convenient, allowing the user to modify the parameters while hearing the differences without having to repeat the IR file loading procedure.