Search papers, labs, and topics across Lattice.
EURECOM
6
0
7
Phoneme-level insights reveal the hidden linguistic cues that differentiate real speech from deepfakes, enhancing trust in detection systems.
Linguistic bias in spoofing detection can lead to a staggering 36.2% increase in error rates when models encounter out-of-domain data.
Naive data scaling can actually harm performance in voice spoofing detection, while just 8 hours of fine-tuning can dramatically boost robustness.
Speaker-invariant spoofing detection can be achieved without speaker labels, leading to a dramatic 25.7% improvement in detection accuracy across diverse datasets.
Multi-corpus training can actually *hurt* spoofing detection, unless you strip out dataset-specific biases with this clever domain-invariant feature extraction trick.
Speaker identity significantly impacts spoofing detection, and surprisingly, removing speaker-specific information from embeddings can dramatically improve performance, especially against sophisticated attacks.
