SBIR Phase II: iGlasses: An Appliance for Improving Speech Understanding in Face-to-Face Communication and Classroom Situations

这个小型企业创新研究(SBIR)第二阶段项目将完成技术的开发，以补充数百万聋人或重听人或面临其他语言/语言挑战的人的普通面对面语言互动。该项目的目标是使这些人能够充分参与口语社区。在当今世界，对语言和语音可理解性辅助工具的需求无处不在。数以百万计的人生活在语言和言语方面的挑战中(例如3600万美国听力障碍者)，这些人需要额外的沟通和语言学习支持。第一阶段的研究开发并测试了iGlass的行为科学和技术。在这项研究的基础上，拟议的研究将完成一种创新的干预措施并将其推向市场，这种干预措施可以将口语和文化带入目前因听力丧失或其他言语/语言障碍而被边缘化的人的生活中。这项拟议的研究将推动人机交互、语音、机器学习和辅助技术的发展。该项目的更广泛的商业影响将使聋人和重听人口以及科学界受益，因为它为几乎所有人都能以非常低的成本自然获得的言语援助提供了研究和理论基础。它不需要识字用户，因为不像字幕系统中那样呈现书面信息；它与年龄无关，因为它可能被蹒跚学步的儿童、青少年和整个生命周期使用；它对所有语言都是有效的，因为它是独立于语言的，因为所有语言都具有相同的语音特征，具有高度相似的相应声学特征；它将为戴助听器和植入人工耳蜗的人提供重大帮助；它将对许多语言有语言障碍的人，甚至对儿童学习阅读有利。最后，无论语音识别技术有没有进步，提取语音的基本声学特征总是比识别整个音素更准确和有效，因为整个音素是这些基本特性的更复杂组合。

This Small Business Innovation Research (SBIR) Phase II project will complete the development of technology to supplement ordinary face-to-face language interaction for the millions of individuals who are deaf or hard of hearing or face other speech/language challenges. The goal of the project is to enable such individuals to fully participate in the spoken language community. The need for language and speech intelligibility aids is pervasive in today's world. Millions of individuals live with language and speech challenges (such as 36 million Americans with hearing deficits), and these individuals require additional support for communication and language learning. The Phase I research developed and tested the behavioral science and technology for iGlasses. Building on this research, the proposed research is to complete and bring to market an innovative intervention that can bring spoken language and culture into the lives of individuals who are currently marginalized because of hearing loss or other speech/language challenges. The proposed research will advance the state of the art in human machine interaction, speech, machine learning, and assistive technologies. The broader/commercial impact of this project will benefit the deaf and hard-of-hearing populations as well as the scientific community by providing a research and theoretical foundation for a speech aid that would be naturally available to almost all individuals at a very low cost. It does not require literate users because no written information is presented as would be the case in a captioning system; it is age-independent in that it might be used by toddlers, adolescents, and throughout the lifespan; it is functional for all languages because it is language independent given that all languages share the same phonetic features with highly similar corresponding acoustic characteristics; it would provide significant help for people with hearing aids and cochlear implants; and it would be beneficial for many individuals with language challenges and even for children learning to read. Finally, regardless of the advances or lack of advances in speech recognition technology, it will always be more accurate and effective to pick off the fundamental acoustic features of speech than it is to recognize entire phonemes which are more complex combinations of these basic properties.