In this paper, we propose a novel lip-to-speech system that significantly improves the generation quality by alleviating the one-to-many mapping problem from multiple perspectives.
In this paper, we propose CrossSpeech which improves the quality of cross-lingual speech by effectively disentangling speaker and language information in the level of acoustic feature space.
To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner.
In this paper, we propose a computational storage platform that can accelerate a large-scale graph-based nearest neighbor search algorithm based on SmartSSD CSD.
These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models.
To take such non-linear characteristics into account, we introduce Label-Gradient Alignment (LGA), a novel NTK-based metric whose inherent formulation allows it to capture the large amount of non-linear advantage present in modern neural architectures.
We propose Supernet with Unbiased Meta-Features for Neural Architecture Search (SUMNAS), a supernet learning strategy based on meta-learning to tackle the knowledge forgetting issue.
While numerous attempts have been made to the few-shot speaker adaptation system, there is still a gap in terms of speaker similarity to the target speaker depending on the amount of data.
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space.
Data augmentation tuned to datasets and tasks has had great success in various AI applications, such as computer vision, natural language processing, autonomous driving, and bioinformatics.
This paper introduces a method that efficiently reduces the computational cost and parameter size of Transformer.
With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases.
HyperTendril takes a novel approach to effectively steering hyperparameter optimization through an iterative, interactive tuning procedure that allows users to refine the search spaces and the configuration of the AutoML method based on their own insights from given results.
We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.
The checkerboard phenomenon is one of the well-known visual artifacts in the computer vision field.
Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance.
no code implementations • 11 Aug 2018 • Tsung-Ting Kuo, Jina Huh, Ji-Hoon Kim, Robert El-Kareh, Siddharth Singh, Stephanie Feudjio Feupe, Vincent Kuri, Gordon Lin, Michele E. Day, Lucila Ohno-Machado, Chun-Nan Hsu
Our study introduces CLEAN (CLinical note rEview and ANnotation), a pre-annotation-based cNLP annotation system to improve clinical note annotation of data elements, and comprehensively compares CLEAN with the widely-used annotation system Brat Rapid Annotation Tool (BRAT).