Switching divergences for spectral learning in blind speech dereverberation
This addresses audio quality issues in human-machine interaction technologies, but appears incremental as it builds on existing spectral learning methods.
The authors tackled blind speech dereverberation by proposing a two-stage approach using a generalized β-divergence for spectral learning and reverberation modeling, showing improvements over state-of-the-art methods on artificial and real recordings.
When recorded in an enclosed room, a sound signal will most certainly get affected by reverberation. This not only undermines audio quality, but also poses a problem for many human-machine interaction technologies that use speech as their input. In this work, a new blind, two-stage dereverberation approach based in a generalized β-divergence as a fidelity term over a non-negative representation is proposed. The first stage consists of learning the spectral structure of the signal solely from the observed spectrogram, while the second stage is devoted to model reverberation. Both steps are taken by minimizing a cost function in which the aim is put either in constructing a dictionary or a good representation by changing the divergence involved. In addition, an approach for finding an optimal fidelity parameter for dictionary learning is proposed. An algorithm for implementing the proposed method is described and tested against state-of-the-art methods. Results show improvements for both artificial reverberation and real recordings.