A Feature Learning Siamese Model for Intelligent Control of the Dynamic Range Compressor
This work addresses the challenge of automating DRC configuration for audio professionals in music production, speech, and broadcasting, representing an incremental improvement over previous research.
The authors tackled the problem of configuring dynamic range compressors (DRC) by proposing a siamese DNN model that learns feature embeddings from audio examples, enabling intelligent control. The best model achieved better performance than handcrafted features in predicting DRC parameters for both mono-instrument and polyphonic audio.
In this paper, a siamese DNN model is proposed to learn the characteristics of the audio dynamic range compressor (DRC). This facilitates an intelligent control system that uses audio examples to configure the DRC, a widely used non-linear audio signal conditioning technique in the areas of music production, speech communication and broadcasting. Several alternative siamese DNN architectures are proposed to learn feature embeddings that can characterise subtle effects due to dynamic range compression. These models are compared with each other as well as handcrafted features proposed in previous work. The evaluation of the relations between the hyperparameters of DNN and DRC parameters are also provided. The best model is able to produce a universal feature embedding that is capable of predicting multiple DRC parameters simultaneously, which is a significant improvement from our previous research. The feature embedding shows better performance than handcrafted audio features when predicting DRC parameters for both mono-instrument audio loops and polyphonic music pieces.