Semi-supervised source localization with deep generative modeling
This work addresses localization challenges in acoustics for applications like robotics or audio processing, but it is incremental as it adapts existing SSL and VAE methods to a specific domain problem.
The paper tackled the problem of sound source localization in reverberant environments with limited labeled data by proposing a semi-supervised approach using variational autoencoders (VAEs) and a DOA classifier, finding that it outperformed SRP-PHAT and fully-supervised CNNs in label-limited scenarios.
We propose a semi-supervised localization approach based on deep generative modeling with variational autoencoders (VAEs). Localization in reverberant environments remains a challenge, which machine learning (ML) has shown promise in addressing. Even with large data volumes, the number of labels available for supervised learning in reverberant environments is usually small. We address this issue by performing semi-supervised learning (SSL) with convolutional VAEs. The VAE is trained to generate the phase of relative transfer functions (RTFs), in parallel with a DOA classifier, on both labeled and unlabeled RTF samples. The VAE-SSL approach is compared with SRP-PHAT and fully-supervised CNNs. We find that VAE-SSL can outperform both SRP-PHAT and CNN in label-limited scenarios.