Zobrazeno 1 - 10
of 3 020
pro vyhledávání: '"Wang Lun"'
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Liu, Hongbin, Chen, Youzheng, Narayanan, Arun, Balachandran, Athula, Moreno, Pedro J., Wang, Lun
Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like misinforma
Externí odkaz:
http://arxiv.org/abs/2410.06572
Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is computationally expensive, and can hurt model performance. Our study
Externí odkaz:
http://arxiv.org/abs/2410.01948
The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rend
Externí odkaz:
http://arxiv.org/abs/2409.09582
Autor:
Wang, Lun
Micro-batch clipping, a gradient clipping method, has recently shown potential in enhancing auto-speech recognition (ASR) model performance. However, the underlying mechanism behind this improvement remains mysterious, particularly the observation th
Externí odkaz:
http://arxiv.org/abs/2408.16204
Large Language Models (LLMs) have achieved remarkable progress in language understanding and generation. Custom LLMs leveraging textual features have been applied to recommendation systems, demonstrating improvements across various recommendation sce
Externí odkaz:
http://arxiv.org/abs/2406.12243
The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embedding human-imperceptible watermar
Externí odkaz:
http://arxiv.org/abs/2406.06979