ENVIRONMENTAL SOUND RECOGNITION

描述：（改编自申请人的摘要）提出： 继续开发听力辅助设备， 受损 该装置将监测声学环境以检测和 将单独的声音与背景噪音分开，并将它们彼此分开。 它 能识别熟悉的声音 它会描述不熟悉的声音， 它们与已知声音的相似性以及与之相关的定性术语 到感知概念，如响度、持续时间、音高和不稳定性。 多麦克风版本还可以提供关于 来源的位置。 第二阶段的研究目标是提高识别 声音事件，声音的感知描述，以及 语音识别。 开发的目标是制造一个原型 一种装置，装在一台笔记本电脑里，可以识别100种不同的 在真实的时间里发出声音，并描述任何它不能识别的声音。 当 通过多麦克风阵列增强，该设备应展示 声音定位能力和改进的同步声音处理。

DESCRIPTION: (Adapted From the Applicant's Abstract) It is proposed to continue the development of an assistive listening device for the hearing- impaired. This device would monitor the acoustic environment to detect and separate individual sounds from background noise and from each other. It would identify familiar sounds. It would describe unfamiliar sounds in terms of their similarity to known sounds and in qualitative terms related to perceptual notions such as loudness, duration, pitch, and abruptness. A multiple-microphone version could also provide information on the location of sources. The research goals of Phase II are to improve the identification of acoustic events, the perceptual description of sounds, and the identification of speech. The developmental goal is to make a prototype device, packaged in a lap-top computer, that can recognize 100 different sounds in real time, and describe any sounds it can't recognize. When enhanced with a multiple-microphone array, this device should demonstrate sound localization capability and improved handling of simultaneous sounds.