arXiv:2203.16263v5 Announce Type: replace-cross
Abstract: Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for dete…
arXiv:2603.24596v1 Announce Type: cross
Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance d…
arXiv:2603.24651v1 Announce Type: new
Abstract: Automatic depression detection from doctor-patient conversations has gained momentum thanks to the availability of public corpora and advances in language modeling. However, interpretability remains limi…
arXiv:2603.23723v1 Announce Type: cross
Abstract: Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known directions. To retain this level of performance in dynamic scenar…
arXiv:2602.12304v3 Announce Type: replace-cross
Abstract: Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of join…
arXiv:2603.23667v1 Announce Type: cross
Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 3,577 tracks (110 hour…