Human-computer interaction system: A survey of talking-head generation
Virtual human is widely employed in various industries, including personal assistance,
intelligent customer service, and online education, thanks to the rapid development of …
intelligent customer service, and online education, thanks to the rapid development of …
Alchemy: Data-Free Adversarial Training
Y Bai, Z Ma, Y Chen, J Deng, S Pang, Y Liu… - Proceedings of the 2024 …, 2024 - dl.acm.org
Machine learning models have become integral to various aspects of daily life, prompting
increased vulnerability to adversarial attacks. Adversarial training is one of the most …
increased vulnerability to adversarial attacks. Adversarial training is one of the most …
[PDF][PDF] Speech generation for indigenous language education
RK Kazantsevaa, R Kuhna, S Larkina… - Computer Speech & …, 2024 - docs.everyvoice.ca
The vast majority of the world's languages are unable to follow in the footsteps of existing
resource-intensive pathways to building text-to-speech (TTS) systems. But, as the quality of …
resource-intensive pathways to building text-to-speech (TTS) systems. But, as the quality of …
Grammar-supervised end-to-end speech recognition with part-of-speech tagging and dependency parsing
For most automatic speech recognition systems, many unacceptable hypothesis errors still
make the recognition results absurd and difficult to understand. In this paper, we introduce …
make the recognition results absurd and difficult to understand. In this paper, we introduce …
Looking and listening: Audio guided text recognition
Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-
end deep learning, recent studies suggest vision and language processing are effective for …
end deep learning, recent studies suggest vision and language processing are effective for …