A Real-time, Open, Portable, Extensible Speech Lab

实时、开放、便携式、可扩展的语音实验室

• 批准号: 9753728
• 负责人: Harinath Garudadri
• 金额: $ 37.79万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN DIEGO
• 依托单位国家: 美国
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-08-01 至 2021-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9753728
• 关键词: Acoustics; Algorithms; Audiology; Binaural; Cellular Phone; Characteristics; Clinical; Communities; Computer software; Data Collection; Development; Devices; Ear; Engineering; Ensure; Environment; Evaluation; Feedback; Fostering; Future; Generations; Goals; Health Care Research; Healthcare; Hearing; Hearing Aids; Instruction; Intellectual Property; Laboratories; Libraries; Longevity; Noise; Output; Property Rights; Protocols documentation; Publishing; Reporting; Research; Research Personnel; Running; Sampling; Science; Scientist; Signal Transduction; Software Engineering; Source Code; Speech; Speech Intelligibility; System; Technology; Testing; Time; Translations; Validation; Vision; Wireless Technology; base; clinical practice; design; digital; engineering design; field study; hearing impairment; improved; innovation; novel; open source; portability; prevent; research study; response; signal processing; skills; speech processing; tool; wearable device

ABSTRACT Current efforts to improve speech intelligibility in hearing aids using signal processing algorithms are hampered by the need to reinvent realtime processing tools across research labs. Intellectual property rights and monetary considerations prevent the open sharing of processing tools from commercial companies and limit the usefulness of commercially available hearing aids in research. As a result, many academic innovations that could potentially improve hearing health care are not being tested and evaluated. Furthermore, when closed, proprietary devices are used in academic research, it becomes difficult to assess the impact of the findings when pertinent details of the subsystems in the signal processing pipeline are not known. In this proposal, we aim to develop an open, reconfigurable, non-proprietary, wearable, realtime speech processing system that uses processing and data collection approaches not available in existing hearing-aid technology that Audiologists and hearing aid researchers will be able to easily use to investigate new hearing aid algorithms in lab and field studies. Using novel speech processing algorithms, this open-access tool specifically designed for audiologists and hearing aid researchers will help accelerate hearing health care research studies and facilitate translation of technology advances into widespread clinical use.

抽象的 目前使用信号处理算法提高助听器语音清晰度的努力受到阻碍 由于需要重新发明跨研究实验室的实时处理工具。知识产权和 货币方面的考虑阻碍了商业公司公开共享处理工具并限制了 市售助听器在研究中的用途。由此产生了许多学术创新 可能改善听力保健的技术尚未得到测试和评估。此外，当 学术研究中使用封闭的专有设备，因此很难评估其影响 当信号处理管道中子系统的相关细节未知时的发现。在这个 提案中，我们的目标是开发一种开放的、可重构的、非专有的、可穿戴的、实时的语音处理 使用现有助听器技术所不具备的处理和数据收集方法的系统 听力学家和助听器研究人员将能够轻松地使用它来研究新的助听器 实验室和现场研究中的算法。这种开放访问工具使用新颖的语音处理算法 专为听力学家和助听器研究人员设计，将有助于加速听力保健 研究并促进技术进步转化为广泛的临床应用。