4 accepted papers
In this work, we introduce a multi-task transformer for speech deepfake detection, capable of predicting formant trajectories and voicing patterns over time, ultimately classifying speech as real or fake, and highlighting whether its decisions rely more on voiced or unvoiced regions. Building on a p…
This paper introduces a novel multi-task transformer for synthetic speech detection. The network encodes magnitude and phase of the input speech with a feature bottleneck, used to autoencode the input magnitude, to predict the trajectory of the fundamental frequency (f0), and to discern if the input…
In this paper, we propose a new method for AAC encoding detection and bitrate estimation from PCM material. The algorithm is based on a Convolutional Neural Network that can distinguish between eight different bitrates. It achieves an average accuracy of 94.65% by analysis of only 116.10 ms of conte…
In this paper, we present a new algorithm for open-set microphone classification, which is based on a pre-existing blind channel estimation approach. The proposed method achieves a Rand index above 93% for AAC, MP3 and PCM-encoded recordings from eight different mobile devices.