Speaker: Mauricio Michel Olvera Zambrano
Data and place: May 19, 2022, at 10:30 – Hybrid
Abstract: Acoustic scene classification systems face performance degradation when trained and tested on data recorded by different devices. Unsupervised domain adaptation methods have been studied to reduce the impact of this mismatch. While they do not assume the availability of labels at test time, they often exploit parallel data recorded by both devices and thus are not fully blind to the target domain. In this talk, I will address a more practical scenario where parallel data are not available and analyze the impact of normalization and moment matching strategies to compensate for the linear distortion introduced by the recording device, and propose their integration with adversarial domain adaptation to handle the remaining non-linear distortion.