Superb: Speech processing universal performance benchmark
Self-supervised learning (SSL) has proven vital for advancing research in natural language
processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on …
processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on …
[HTML][HTML] The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens
Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global,
community-driven effort to evaluate and improve the computational annotation of protein …
community-driven effort to evaluate and improve the computational annotation of protein …
Comorbidity profiles among patients with alopecia areata: the importance of onset age, a nationwide population-based study
BACKGROUND: Alopecia areata (AA) is considered an autoimmune disease with
undetermined pathogenesis. Age at onset predicts distinct outcomes. A nationwide study of the …
undetermined pathogenesis. Age at onset predicts distinct outcomes. A nationwide study of the …
Offline multi-agent reinforcement learning with knowledge distillation
We introduce an offline multi-agent reinforcement learning (offline MARL) framework that
utilizes previously collected data without additional online data collection. Our method …
utilizes previously collected data without additional online data collection. Our method …
U‐shaped association between serum uric acid levels with cardiovascular and all‐cause mortality in the elderly: the role of malnourishment
Background The link between elevated serum uric acid ( SUA ) levels and cardiovascular
disease ( CVD )–related mortality in the elderly population remains inconclusive. Nutritional …
disease ( CVD )–related mortality in the elderly population remains inconclusive. Nutritional …
Malignancies after renal transplantation in Taiwan: a nationwide population-based study
Background. Renal transplantation has been regarded as the treatment of choice for end-stage
renal disease. Renal transplantation increases the risk of cancers due to long-term …
renal disease. Renal transplantation increases the risk of cancers due to long-term …
Speechprompt: An exploration of prompt tuning on generative spoken language model for speech processing tasks
Speech representations learned from Self-supervised learning (SSL) models can benefit
various speech processing tasks. However, utilizing SSL representations usually requires fine-…
various speech processing tasks. However, utilizing SSL representations usually requires fine-…
Utilizing self-supervised representations for MOS prediction
Speech quality assessment has been a critical issue in speech processing for decades.
Existing automatic evaluations usually require clean references or parallel ground truth data, …
Existing automatic evaluations usually require clean references or parallel ground truth data, …
Speechprompt v2: Prompt tuning for speech classification tasks
Prompt tuning is a technology that tunes a small set of parameters to steer a pre-trained
language model (LM) to directly generate the output for downstream tasks. Recently, prompt …
language model (LM) to directly generate the output for downstream tasks. Recently, prompt …
Cla-nerf: Category-level articulated neural radiance field
We propose CLA-NeRF - a Category-Level Articulated Neural Radiance Field that can perform
view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained …
view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained …