Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6951497 | Computer Speech & Language | 2018 | 50 Pages |
Abstract
As term of comparison, two algorithms proposed in literature for the addressed applicative context are evaluated, the Crosspower Spectrum Phase Speaker Localization (CSP-SLOC) and the Steered Response Power using the Phase Transform speaker localization (SRP-SLOC). Besides providing an extensive analysis of the proposed method, the article shows how DNN-based algorithm significantly outperforms the state-of-the-art approaches evaluated on the DIRHA dataset, providing an average localization error, expressed in terms of Root Mean Square Error (RMSE), equal to 324Â mm and 367Â mm, respectively, for the Simulated and the Real subsets.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Fabio Vesperini, Paolo Vecchiotti, Emanuele Principi, Stefano Squartini, Francesco Piazza,