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

SBIR 第一阶段：iGlasses：用于提高面对面交流和课堂情境中语音理解的设备

• 批准号: 0839802
• 负责人: Michael Cohen
• 金额: $ 9.99万
• 依托单位: Animated Speech Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-01-01 至 2009-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0839802&HistoricalAwards=false
• 关键词: SBIR; Phase; iGlasses; Appliance; Improving

This Small Business Innovation Research (SBIR) project will advance the state of the art in human machine interaction, speech, machine learning and assistive technologies. The innovation in the proposed research is to develop and test the technology required to design an embellished eyeglass, which will perform continuous real-time acoustic analysis of the interlocutor's speech and transform several continuous acoustic features of the user's speech into continuous visual features displayed on the eyeglasses. Pilot research has demonstrated that it is possible to recognize robust characteristics of isolated auditory words and to transform them into visible features in real time. The proposed research extends this research to sentences along with tests of different feature detectors and automatic recognition models. The proposed activity will impact society by providing a research and theoretical foundation for a system that would be available to 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 life span; 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.

这个小企业创新研究（SBIR）项目将推进人机交互，语音，机器学习和辅助技术的最新发展。在拟议的研究中的创新是开发和测试所需的技术来设计一个装饰的眼镜，这将执行对话者的语音连续实时声学分析，并转换成连续的视觉特征显示在眼镜上的用户的语音的几个连续的声学特征。初步研究表明，有可能识别孤立的听觉词的鲁棒特征，并将其转换为真实的可见特征。拟议中的研究扩展到句子沿着不同的特征检测器和自动识别模型的测试。拟议的活动将通过为一个以极低成本向所有人提供的系统提供研究和理论基础来影响社会。它不需要识字的用户，因为不像字幕系统那样提供书面信息;它与年龄无关，因为它可以由幼儿、青少年和整个生命周期使用;它适用于所有语言，因为它与语言无关，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;它将为有助听器和人工耳蜗植入的人提供重要帮助;它将有益于许多有语言障碍的人，甚至有益于学习阅读的儿童。