1 code implementation • 14 Apr 2021 • Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain.
no code implementations • 8 Apr 2019 • Vivek Sivaraman Narayanaswamy, Sameeksha Katoch, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias
We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow.
no code implementations • 1 Nov 2018 • Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias
State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identities to unseen data.