Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Chen, Xuanjun"'
Automatic Speaker Verification (ASV), increasingly used in security-critical applications, faces vulnerabilities from rising adversarial attacks, with few effective defenses available. In this paper, we propose a neural codec-based adversarial sample
Externí odkaz:
http://arxiv.org/abs/2406.04582
Autor:
Wu, Haibin, Chen, Xuanjun, Lin, Yi-Cheng, Chang, Kai-wei, Chung, Ho-Lam, Liu, Alexander H., Lee, Hung-yi
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into discrete codes,
Externí odkaz:
http://arxiv.org/abs/2402.13236
Autor:
Wu, Haibin, Chung, Ho-Lam, Lin, Yi-Cheng, Wu, Yuan-Kuei, Chen, Xuanjun, Pai, Yu-Chi, Wang, Hsiu-Hsuan, Chang, Kai-Wei, Liu, Alexander H., Lee, Hung-yi
The sound codec's dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance. Recent years have witnessed significant developments in codec models. The ideal sound codec should preserve content, pa
Externí odkaz:
http://arxiv.org/abs/2402.13071
Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. Ho
Externí odkaz:
http://arxiv.org/abs/2210.15563
Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, n
Externí odkaz:
http://arxiv.org/abs/2210.00753
The countermeasure (CM) model is developed to protect ASV systems from spoof attacks and prevent resulting personal information leakage in Automatic Speaker Verification (ASV) system. Based on practicality and security considerations, the CM model is
Externí odkaz:
http://arxiv.org/abs/2203.17031
Due to the rapid development of deep learning, we can now successfully separate singing voice from mono audio music. However, this separation can only extract human voices from other musical instruments, which is undesirable for karaoke content gener
Externí odkaz:
http://arxiv.org/abs/2110.06707