Diffusion-based speech enhancement has shown promising results, but can
suffer from a slower inference time. Initializing the diffusion process with
the enhanced audio generated by a regression-based model can be used to reduce
the computational steps required. However, these approaches often necessitate a
regression model, further increasing the system's complexity. We propose
Thunder, a unified regression-diffusion model that utilizes the Brownian bridge
process which can allow the model to act in both modes. The regression mode can
be accessed by setting the diffusion time step closed to 1. However, the
standard score-based diffusion modeling does not perform well in this setup due
to gradient instability. To mitigate this problem, we modify the diffusion
model to predict the clean speech instead of the score function, achieving
competitive performance with a more compact model size and fewer reverse steps.

通过使用基于扩散的语音增强方法，初始化扩散过程以改进音频，并使用回归模型可以减少计算步骤，提出了一种名为 Thunder 的统一回归 - 扩散模型，该模型利用布朗桥过程可在两种模式下运行，通过将扩散时间步骤设置为接近 1 可访问回归模式，但是标准得分扩散建模在此设置中性能不佳，为了缓解这个问题，我们修改了扩散模型以预测干净的语音而不是得分函数，从而以更紧凑的模型大小和更少的反向步骤实现了具有竞争力的性能。

Thunder: 一种使用布朗桥进行单向反演步骤的统一回归扩散语音增强方法

Thunder : Unified Regression-Diffusion Speech Enhancement with a Single  Reverse Step using Brownian Bridge

Neural networks and in particular the attention mechanism have brought
significant advances to the field of Automated Essay Scoring. Many of these
systems use a regression-based model which may be prone to underfitting when
the model only predicts the mean of the training data. In this paper, we
present a dynamic loss function that creates an incentive for the model to
predict with the correct distribution, as well as predicting the correct
values. Our loss function achieves this goal without sacrificing any
performance achieving a Quadratic Weighted Kappa score of 0.752 on the
Automated Student Assessment Prize Automated Essay Scoring dataset.

该研究利用动态损失函数建立基于神经网络和注意机制的自动化作文评分模型，能够避免回归模型预测训练样本均值的欠拟合现象，并在测试集上取得 Quadratic Weighted Kappa 得分 0.752。

神经网络自动化评分中动态损失函数的有效性

The Effectiveness of a Dynamic Loss Function in Neural Network Based  Automated Essay Scoring

This paper addresses the problem of text-to-video temporal grounding, which
aims to identify the time interval in a video semantically relevant to a text
query. We tackle this problem using a novel regression-based model that learns
to extract a collection of mid-level features for semantic phrases in a text
query, which corresponds to important semantic entities described in the query
(e.g., actors, objects, and actions), and reflect bi-modal interactions between
the linguistic features of the query and the visual features of the video in
multiple levels. The proposed method effectively predicts the target time
interval by exploiting contextual information from local to global during
bi-modal interactions. Through in-depth ablation studies, we find out that
incorporating both local and global context in video and text interactions is
crucial to the accurate grounding. Our experiment shows that the proposed
method outperforms the state of the arts on Charades-STA and ActivityNet
Captions datasets by large margins, 7.44\% and 4.61\% points at Recall@tIoU=0.5
metric, respectively. Code is available in
this https URL

该论文提出了一种基于回归模型的方法，使用文本查询中的语义短语提取中间特征，以反映查询中描述的重要语义实体和视频的视觉特征之间的双模态交互，通过在多个层面上从局部到全局利用上下文信息，有效地预测目标时间区间。实验证明，该方法在 Charades-STA 和 ActivityNet Captions 数据集上的表现明显优于现有方法。