Real-time deep learning to improve speech intelligibility in noise

实时深度学习提高噪声中的语音清晰度

• 批准号: 10268203
• 负责人: Eric Martin Johnson
• 金额: $ 7.01万
• 依托单位: OHIO STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-30 至 2022-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10268203
• 关键词: Address; Algorithms; American; Area; Auditory; Cellular Phone; Characteristics; Cochlear Implants; Communication; Complex; Data; Devices; Diagnosis; Economic Burden; Effectiveness; Environment; Equilibrium; Etiology; Faculty; Fellowship; Floor; Foundations; Future; Goals; Healthcare; Hearing; Hearing Aids; Human; Implant; Measures; Mentors; Mission; National Institute on Deafness and Other Communication Disorders; Noise; Performance; Phase; Prevention; Process; Quality of life; Recommendation; Research; Research Personnel; Research Training; Scheme; Seminal; Signal Transduction; Speech; Speech Intelligibility; Strategic Planning; System; Telephone; Testing; Time; Training; Translating; Universities; Videoconferencing; Work; artificial neural network; base; career; communication device; deep learning; deep neural network; design; experimental study; health economics; hearing impairment; hearing loss treatment; improved; microphone; network architecture; neural network; normal hearing; novel; novel strategies; operation; skills; speech in noise; wearable device

Project Summary/Abstract One in eight Americans has hearing loss, and this constitutes a major health and economic burden (Blackwell et al., 2014). The primary complaint of hearing-impaired (HI) listeners is difficulty understanding speech when background noise is present (see Dillon, 2012). While hearing aids (HAs) have improved in recent years, they still provide little benefit in noisy environments. For decades, a means of improving the ability to understand speech in background noise appeared unattainable, despite substantial amounts of research by both universities and HA companies. This changed when deep learning provided the first demonstration of a single-microphone algorithm that improves intelligibly in noise for HI listeners (Healy et al., 2013, 2014, 2015). Although this algorithm provides massive intelligibility improvements (even allowing listeners to improve intelligibility from floor to ceiling levels), it is currently not implemented to operate in real time and is therefore not suitable for implementation into HAs and cochlear implants (CIs). What is needed, therefore, is a highly effective noise-reduction algorithm that is capable of operating in real time. This project aims to address this critical need. The long-term goal of the currently proposed project is to alleviate HI listeners’ predominant hearing handicap, which is difficulty understanding speech in background noise. The first aim introduces a new algorithm, based on a novel foundational scheme, that is designed to provide substantial benefit for any HI listener in real time. This algorithm will be well suited for implementation into HAs, CIs, and other face-to-face communication applications. The effectiveness of this new algorithm will be quantified using both HI and normal-hearing (NH) listeners. The second aim expands upon this new algorithm by modifying it to accept a small amount of future time-frame information, which could improve its noise-reduction performance but will introduce a brief processing delay. The rationale is that different devices have different allowable latencies. Face-to-face communication devices (HAs, CIs, etc.) have strict low-latency requirements, but other important communication systems (e.g., telephones) have different requirements. It is possible that the addition of future time-frame information within these requirements (up to 150 ms) will result in even better speech intelligibility. But the magnitude of any potential benefit is unknown. This critical information will be established currently. Using both HI and NH listeners, we will measure intelligibility for noisy sentences that have been processed using various amounts of future time information. This comprehensive fellowship training plan will provide individualized, mentored research training from world-class faculty in a highly supportive and productive environment. The proposed work will endow the applicant with the skills needed to transition to the next stage of his research career, transform our treatment of hearing loss, and substantially impact quality of life for millions of Americans.

项目摘要/摘要 八分之一的美国人有听力损失，这构成了主要的健康和经济伯恩 （Blackwell等，2014）。听力受损（HI）听众的主要抱怨很难理解 存在背景噪声时的语音（见Dillon，2012年）。虽然助听器（有）有所改善 近年来，它们在噪声环境中仍然几乎没有好处。几十年来，一种改善的手段 在背景噪音中理解语音的能力似乎是无法实现的，目的地大量数量 大学和HA公司的研究。当深度学习提供第一个时，情况发生了变化 一种单微粒算法的演示，该算法可以在HI听众的噪声方面明显改善（Healy等，， 2013，2014，2015）。尽管该算法可提供大规模的情报改进（甚至允许 听众可以提高从地板到天花板水平的清晰度），目前尚未实施实际运作 时间，因此不适合实施HAS和人工耳蜗（CI）。需要什么 因此，是一种能够实时运行的高效降噪算法。这个项目 旨在满足这一关键需求。 当前提议的项目的长期目标是减轻听众的主要听力 障碍，这很难理解背景噪声中的语音。第一个目标引入了新的 基于一种新颖的基础方案，算法旨在为任何HI提供可观的好处 实时听众。该算法将非常适合实施HAS，CI和其他面对面 通信应用。该新算法的有效性将使用HI和HI和 正常听众（NH）听众。第二个目标通过修改以接受一个新算法来扩展该算法 少量的将来的时间框架信息可以改善其降噪性能，但会提高 引入简短的处理延迟。理由是不同的设备具有不同的允许潜伏期。 面对面的通信设备（具有，顺式等）具有严格的低延迟要求，但其他重要的 通信系统（例如电话）有不同的要求。未来可能会增加 这些需求中的时间范围信息（长达150毫秒）将带来更好的语音智能。 但是任何潜在益处的幅度尚不清楚。目前将建立此关键信息。 使用HI和NH听众，我们将测量已处理的噪声句子的清晰度 使用各种未来的时间信息。 这项全面的奖学金培训计划将提供来自 世界一流的教职员工在高度支持和富有成效的环境中。拟议的工作将赋予 申请人具有过渡到其研究职业下一阶段所需的技能，改变了我们的对待 听力损失，并严重影响数百万美国人的生活质量。