arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.08968cs.ETcs.SD
收藏

小语音数据集发声障碍评估的量子方法

Quantum Approaches for Dysphonia Assessment in Small Speech Datasets

Deakin University(迪肯大学);School of Engineering(工程学院);Networked Sensing & Biomedical Engineering (NSBE) Research lab(网络传感与生物医学工程研究实验室)

Ha Tran, Bipasha Kashyap, Pubudu N. Pathirana

AI总结:

针对小语音数据集下发声障碍评估中CNN性能受限的问题,本研究对比CNN与新型混合量子-经典方法QNNs的表现,发现QNNs在准确性和稳定性上持续优于CNN,为小数据集发声障碍评估提供新方案。

摘要:

发声障碍是一种常见的医学状况,会导致声音丧失、嘶哑或言语中断。为评估该病症,研究人员一直在传统医学评估之外研究各种机器学习技术。卷积神经网络(CNNs)因其在音频分类和语音识别中的成功而受到关注。然而,语音数据的有限可用性对CNNs构成挑战。本研究评估了CNNs与一种新型混合量子-经典方法——量子卷积神经网络(QNNs)的性能,后者适用于小数据集。音频数据被预处理为梅尔频谱图,包含243个训练样本和61个测试样本,用于10次实验。开发了4个模型(2个QNNs和2个CNNs),第二个模型加入额外层以提升性能。结果显示,QNN模型在大多数实验中在准确性和稳定性上持续优于CNN模型。

英文摘要:

Dysphonia, a prevalent medical condition, leads to voice loss, hoarseness, or speech interruptions. To assess it, researchers have been investigating various machine learning techniques alongside traditional medical assessments. Convolutional Neural Networks (CNNs) have gained popularity for their success in audio classification and speech recognition. However, the limited availability of speech data, poses a challenge for CNNs. This study evaluates the performance of CNNs against a novel hybrid quantum-classical approach, Quanvolutional Neural Networks (QNNs), which are well-suited for small datasets. The audio data was preprocessed into Mel spectrograms, comprising 243 training samples and 61 testing samples in total, and used in ten experiments. Four models were developed (two QNNs and two CNNs) with the second models incorporating additional layers to boost performance. The results revealed that QNN models consistently outperformed CNN models in accuracy and stability across most experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑