Sound Event Detection with Adaptive Frequency Selection
This work addresses computational efficiency in sound event detection, offering a domain-specific incremental improvement.
The paper tackles efficient sound event detection by introducing HIDACT, a network that adaptively processes frequency bands to reduce computation, achieving comparable performance to more complex baselines.
In this work, we present HIDACT, a novel network architecture for adaptive computation for efficiently recognizing acoustic events. We evaluate the model on a sound event detection task where we train it to adaptively process frequency bands. The model learns to adapt to the input without requesting all frequency sub-bands provided. It can make confident predictions within fewer processing steps, hence reducing the amount of computation. Experimental results show that HIDACT has comparable performance to baseline models with more parameters and higher computational complexity. Furthermore, the model can adjust the amount of computation based on the data and computational budget.