arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.05229cs.SDcs.LGeess.AS
收藏

真实世界自供电间歇设备的语音恢复

Speech Recovery for Real-World Self-powered Intermittent Devices

National Taiwan University(国立台湾大学);Academia Sinica(中央研究院);City University of Hong Kong(香港城市大学);University of California, San Diego(加州大学圣地亚哥分校)

Yu-Chen Lin, Tsun-An Hsieh, Kuo-Hsuan Hung, Cheng Yu, Harinath Garudadri, Yu Tsao, Tei-Wei Kuo

摘要:

语音输入的不完整性严重降低了所有相关语音信号处理应用的性能。虽然已经提出了许多研究来解决这个问题,他们控制的数据丢失的情况下,通过模拟与自定义的掩码长度或大小。此外,掩蔽的定义是不同的所有这些实验设置。本文提出了一种新的间歇性语音恢复(ISR)系统,为现实世界的自供电间歇性设备。三个贡献阶段:插值,增强,并结合应用到ISR系统的语音重建。实验结果表明,我们的恢复系统提高语音质量高达591.7%,同时提高语音清晰度高达80.5%。最重要的是,拟议的ISR系统提高了WER分数高达52.6%。这些有希望的结果不仅证实了重建的有效性,还鼓励了这些无电池可穿戴/物联网设备的使用。

英文摘要:

The incompleteness of speech inputs severely degrades the performance of all the related speech signal processing applications. Although many researches have been proposed to address this issue, they controlled the data missing conditions by simulation with self-defined masking lengths or sizes. Besides, the masking definitions are different among all these experimental settings. This paper presents a novel intermittent speech recovery (ISR) system for real-world self-powered intermittent devices. Three contributive stages: interpolation, enhancement, and combination are applied to the ISR system for speech reconstruction. The experimental results show that our recovery system increases speech quality by up to 591.7%, while increasing speech intelligibility by up to 80.5%. Most importantly, the proposed ISR system improves the WER scores by up to 52.6%. The promising results not only confirm the effectiveness of the reconstruction but also encourage the utilization of these battery-free wearable/IoT devices.

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。

↑