Voice disorders are pathologies significantly affecting patient quality of
life. However, non-invasive automated diagnosis of these pathologies is still
under-explored, due to both a shortage of pathological voice data, and
diversity of the recording types used for the diagnosis. This paper proposes a
novel solution that adopts transformers directly working on raw voice signals
and addresses data shortage through synthetic data generation and data
augmentation. Further, we consider many recording types at the same time, such
as sentence reading and sustained vowel emission, by employing a Mixture of
Expert ensemble to align the predictions on different data types. The
experimental results, obtained on both public and private datasets, show the
effectiveness of our solution in the disorder detection and classification
tasks and largely improve over existing approaches.

声音障碍是显著影响患者生活质量的病理状态。然而，由于病理性声音数据短缺以及用于诊断的录音类型的多样性，对这些病理状态的非侵入性自动诊断仍未得到充分探索。本文提出了一种新颖的解决方案，直接采用在原始声音信号上工作的变压器，并通过合成数据生成和数据增强来解决数据短缺的问题。此外，我们同时考虑了多种录音类型，如句子朗读和持续元音发音，通过采用多模态专家集合来对不同数据类型上的预测进行对齐。在公共和私有数据集上获得的实验结果显示了我们解决方案在障碍检测和分类任务中的有效性，并在现有方法上有了很大的改进。

语音障碍分析：基于 Transformer 的方法

Voice Disorder Analysis: a Transformer-based Approach

Due to the data shortage problem, which is one of the major problems in the
field of machine learning, the accuracy level of many applications remains well
below the expected. It prevents researchers from producing new artificial
intelligence-based systems with the available data. This problem can be solved
by generating new synthetic data with augmentation methods. In this study, new
ECG signals are produced using MIT-BIH Arrhythmia Database by using Generative
Adversarial Neural Networks (GAN), which is a modern data augmentation method.
These generated data are used for training a machine learning system and real
ECG data for testing it. The obtained results show that this way the
performance of the machine learning system is increased.

通过生成对抗网络方法，利用 MIT-BIH 心律失常数据库产生新的 ECG 信号，以增加机器学习系统的性能表现。

使用 GAN 进行数据增强提高非平衡数据集心律失常分类的性能

Data Augmentation with GAN increases the Performance of Arrhythmia Classification for an Unbalanced Dataset

Shortage of available training data is holding back progress in the area of
automated error detection. This paper investigates two alternative methods for
artificially generating writing errors, in order to create additional
resources. We propose treating error generation as a machine translation task,
where grammatically correct text is translated to contain errors. In addition,
we explore a system for extracting textual patterns from an annotated corpus,
which can then be used to insert errors into grammatically correct sentences.
Our experiments show that the inclusion of artificially generated errors
significantly improves error detection accuracy on both FCE and CoNLL 2014
datasets.

本研究探讨了两种替代方法：机器翻译和文本模式提取以解决短缺的数据对自动化错误检测的影响。实验表明：人工生成的错误明显提高了对 FCE 和 CoNLL 2014 数据集的错误检测精度。