Investigating the effects of speech enhancement and compression algorithms for hearing protection devices in noisy environments

研究噪声环境下听力保护设备的语音增强和压缩算法的效果

• 批准号: 520821-2017
• 负责人: Birmingham, Elina
• 金额: $ 1.82万
• 依托单位: Simon Fraser University
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=640428
• 关键词: Investigating; effects; speech; enhancement; compression

Verbal communication in noise while wearing hearing protection devices (HPDs) is often difficult. Ourindustrial partner, EERS, has developed innovative hearing protection, communication and monitoringtechnology for workers of noisy environments. Their industrial hearing protectors (SonX) efficiently block outdamaging noise while allowing workers to communicate over personal radio without removing their devices.In this project, we are planning to implement and evaluate recently developed speech enhancement andcompression algorithms that are designed to maximize speech intelligibility and noise removal while wearingSonX hearing protectors. Critically, the performance of these algorithms has not yet been studied within theelectroacoustic characteristics of the SonX product, which is designed to be used in very noisy environments.In this project, we will first implement these algorithms starting with a versatile PC platform, dubbed theAuditory Research Platform (ARP3), and later on the SonX product at EERS. Then, we will evaluate theperformance of these algorithms by conducting human perceptual testing of speech quality. The results fromthis project will be used by EERS to tune the algorithms for the SonX product and validate their benefits. Thisproject will have significant economic impact by improving the performance and marketability of the highlyinnovative SonX product line. In addition, we will train highly qualified personnel in the areas of biomedicalengineering, information technology, and software development, areas that in high demand in the Canadian jobmarket.

佩戴听力保护装置（HPD）时，在噪音中进行言语交流通常很困难。我们的工业合作伙伴EERS为噪音环境中的工作人员开发了创新的听力保护、通信和监控技术。他们的工业听力保护器（SonX）有效地阻挡了有害的噪音，同时允许工人在不移除他们的设备的情况下通过个人无线电进行通信。在这个项目中，我们计划实施和评估最近开发的语音增强和压缩算法，这些算法旨在最大限度地提高语音清晰度和去除噪音，同时佩戴SonX听力保护器。关键的是，这些算法的性能还没有在SonX产品的电声特性中进行研究，SonX产品被设计用于非常嘈杂的环境中。在这个项目中，我们将首先从一个多功能的PC平台开始实现这些算法，称为听觉研究平台（ARP 3），然后在EERS的SonX产品上实现。然后，我们将评估这些算法的性能进行人类感知测试的语音质量。EERS将使用该项目的结果来调整SonX产品的算法并验证其优势。该项目将通过提高高度创新的SonX产品线的性能和适销性产生重大的经济影响。此外，我们还将在生物医学工程、信息技术和软件开发等加拿大就业市场需求旺盛的领域培养高素质人才。