Project DetailsThis report describes Team SIPLs solution to the 2022 Signal Processing Cup challenge. We developed a method that, given an audio recording of a synthetically generated speech
track, can detect which method among a list of candidates has been used to synthesize the speech, and can also accommodate for unknown speech synthesis algorithms. Our solution relies on speech signal analysis using signal processing and machine learning techniques, particularly deep neural networks. Using an ensemble of features and classifiers allows our method to achieve high performance and to be robust to noise. Another strategy we use for noise robustness is data augmentation for training with noisy audio tracks. Applying our solution to Part 1 of the challenge (noise free samples) yielded an accuracy of 92.2%, and applying it to Part 2 of the challenge (noisy samples) yielded an accuracy of 78.4%.
