Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms
This work addresses the need for more diverse and realistic simulated data in machine listening for researchers and practitioners in audio processing, though it is incremental as it builds on existing simulation tools.
The authors tackled the problem of limited simulated data for sound event localization and detection (SELD) by developing SpatialScaper, a library that emulates virtual rooms with parameters like size and wall absorption, allowing for parameterized placement and movement of sound sources. Using this library to augment the DCASE SELD data led to progressive performance improvements as a function of acoustic diversity.
Sound event localization and detection (SELD) is an important task in machine listening. Major advancements rely on simulated data with sound events in specific rooms and strong spatio-temporal labels. SELD data is simulated by convolving spatialy-localized room impulse responses (RIRs) with sound waveforms to place sound events in a soundscape. However, RIRs require manual collection in specific rooms. We present SpatialScaper, a library for SELD data simulation and augmentation. Compared to existing tools, SpatialScaper emulates virtual rooms via parameters such as size and wall absorption. This allows for parameterized placement (including movement) of foreground and background sound sources. SpatialScaper also includes data augmentation pipelines that can be applied to existing SELD data. As a case study, we use SpatialScaper to add rooms to the DCASE SELD data. Training a model with our data led to progressive performance improves as a direct function of acoustic diversity. These results show that SpatialScaper is valuable to train robust SELD models.