%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 04:58:21 PM @TECHREPORT{Parthasarathi_Idiap-RR-01-2010, author = {Parthasarathi, Sree Hari Krishnan and Magimai.-Doss, Mathew and Bourlard, Herv{\'{e}} and Gatica-Perez, Daniel}, projects = {SNSF-MULTI, IM2}, month = {1}, title = {Evaluating the Robustness of Privacy-Sensitive Audio Features for Speech Detection in Personal Audio Log Scenarios}, type = {Idiap-RR}, number = {Idiap-RR-01-2010}, year = {2010}, institution = {Idiap}, abstract = {Personal audio logs are often recorded in multiple environments. This poses challenges for robust front-end processing, including speech/nonspeech detection (SND). Motivated by this, we investigate the robustness of four different privacy-sensitive features for SND, namely energy, zero crossing rate, spectral flatness, and kurtosis. We study early and late fusion of these features in conjunction with modeling temporal context. These combinations are evaluated in mismatched conditions on a dataset of nearly 450 hours. While both combinations yielded improvements over individual features, generally feature combinations performed better. Comparisons with a state-of-the-art spectral based and a privacy-sensitive feature set are also provided.}, pdf = {https://publications.idiap.ch/attachments/reports/2009/Parthasarathi_Idiap-RR-01-2010.pdf} }