arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00899eess.AScs.SD
收藏

用于无序语音识别的对抗性数据增强

Adversarial Data Augmentation for Disordered Speech Recognition

The Chinese University of Hong Kong(香港中文大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)

Zengrui Jin, Mengzhe Geng, Xurong Xie, Jianwei Yu, Shansong Liu, Xunying Liu, Helen Meng

摘要:

迄今为止,对无序语音的自动识别仍然是一项极具挑战性的任务。潜在的神经运动条件,往往与共同发生的身体残疾,导致难以收集大量的受损语音所需的ASR系统的发展。为此,数据增强技术在当前无序的语音识别系统中起着至关重要的作用。与现有的数据增强技术仅修改说话速率或频谱轮廓的整体形状相比,在数据增强期间使用深度卷积生成对抗网络(DCGAN)对无序和正常语音之间的细粒度频谱-时间差异进行建模,以将正常语音频谱修改为更接近无序语音的频谱。在UASpeech语料库上进行的实验表明,在最先进的混合DNN系统上,所提出的对抗性数据增强方法始终优于使用节奏或速度扰动的基线增强方法。在不使用数据增强的情况下,在基线系统上获得了高达3.05%(相对9.7%)的总体字错误率(WER)降低。最后的学习隐藏单元贡献(LHUC)扬声器适应系统使用最好的对抗增强方法给出了一个整体的WER为25.89%的UASpeech测试集的16个构音障碍的扬声器。

英文摘要:

Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of impaired speech required for ASR system development. To this end, data augmentation techniques play a vital role in current disordered speech recognition systems. In contrast to existing data augmentation techniques only modifying the speaking rate or overall shape of spectral contour, fine-grained spectro-temporal differences between disordered and normal speech are modelled using deep convolutional generative adversarial networks (DCGAN) during data augmentation to modify normal speech spectra into those closer to disordered speech. Experiments conducted on the UASpeech corpus suggest the proposed adversarial data augmentation approach consistently outperformed the baseline augmentation methods using tempo or speed perturbation on a state-of-the-art hybrid DNN system. An overall word error rate (WER) reduction up to 3.05\% (9.7\% relative) was obtained over the baseline system using no data augmentation. The final learning hidden unit contribution (LHUC) speaker adapted system using the best adversarial augmentation approach gives an overall WER of 25.89% on the UASpeech test set of 16 dysarthric speakers.

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。

↑