Empirical Results for Adjusting Truncated Backpropagation Through Time while Training Neural Audio Effects
This work addresses training efficiency and performance for neural audio effects, which is an incremental improvement for audio processing applications.
This paper optimized Truncated Backpropagation Through Time (TBPTT) hyperparameters for training neural networks in digital audio effect modeling, specifically dynamic range compression, and found that careful tuning improved model accuracy, training stability, and computational efficiency while maintaining high perceptual quality.
This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT hyperparameters -- sequence number, batch size, and sequence length -- and their influence on model performance. Using a convolutional-recurrent architecture, we conduct extensive experiments across datasets with and without conditionning by user controls. Results demonstrate that carefully tuning these parameters enhances model accuracy and training stability, while also reducing computational demands. Objective evaluations confirm improved performance with optimized settings, while subjective listening tests indicate that the revised TBPTT configuration maintains high perceptual quality.