Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation
For researchers working on acoustic scene analysis or speaker localization, this work demonstrates that generative RIR augmentation can improve SDE accuracy in data-scarce scenarios, though the method is incremental.
The paper tackles speaker distance estimation (SDE) by augmenting sparse room impulse response (RIR) data with a generative model (FastRIR). The approach reduces mean absolute error from 1.66m to 0.6m for GWA rooms and from 2.18m to 0.69m for Treble rooms, showing significant improvement especially at medium to long distances.
The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR) data for improving SDE model performance. This challenge at GenDARA involves generating RIRs to supplement sparse datasets and fine-tuning SDE models with the augmented data. We employ the open-source fast diffuse room impulse response generator (FastRIR) conditioned only on speaker and listener locations. We design a quality filter to ensure generated RIR alignment with challenge RIRs, and hyperparameter optimization is employed for model fine-tuning. Our approach reduces the mean absolute error (MAE) of the five positions from 1.66m to 0.6m for GWA rooms and from 2.18m to 0.69m for Treble rooms, with results demonstrating that the augmentation approach significantly improves estimation accuracy, particularly at medium to long distances.