Collaborative Research:EAGER:Deep Architectures for Speech and Audio Processing

合作研究：EAGER：语音和音频处理的深度架构

• 批准号: 0957742
• 负责人: Fei Sha
• 金额: $ 5万
• 依托单位: University of Southern California
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-01-01 至 2011-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0957742&HistoricalAwards=false
• 关键词: Collaborative; Research; EAGER; Deep; Architectures

Recent studies have demonstrated the powerful abilities of deep architectures for statistical pattern recognition. Deep architectures transform their inputs through multiple layers of nonlinear processing. Inspired by the connectivity of biological neural networks, the hidden layers of deep architectures encode hierarchical, distributed representations of complex sensory input. Theoretical results suggest that such representations are needed to solve the most difficult problems of artificial intelligence.Previous applications of deep architectures include visual object recognition, statistical language modeling, and nonlinear dimensionality reduction. Building on these successes, this project develops new applications of deep architectures for problems in speech and audio processing. Current front ends for these problems are dominated by traditional methods in statistical modeling and signal processing. Deep architectures have the potential to overcome many limitations of current approaches.This project has two research components with interrelated and overlapping goals. The project's first component explores unsupervised learning in convolutional neural networks. The goal of learning in these networks is to discover new features for audio event detection and automatic speech recognition. The project's second component investigates the possibility of deep learning in kernel machines. This possibility is suggested by a recently discovered family of kernel functions that mimic the computation in large, multilayer networks.The project's research components are tightly integrated with its educational activities. The project supports two graduate students, including one female student. An important goal is to develop publicly available software for use by other researchers.

最近的研究表明，深层结构具有强大的统计模式识别能力。深层体系结构通过多层非线性处理来转换其输入。受生物神经网络连通性的启发，深层结构的隐藏层编码复杂感觉输入的分层、分布式表示。理论结果表明，这种表示是解决人工智能中最困难的问题所必需的。以前深层体系结构的应用包括视觉对象识别、统计语言建模和非线性降维。在这些成功的基础上，该项目开发了针对语音和音频处理问题的深层体系结构的新应用。目前解决这些问题的前端主要是传统的统计建模和信号处理方法。深层体系结构有可能克服当前方法的许多限制。这个项目有两个研究组成部分，它们的目标相互关联和重叠。该项目的第一部分探索卷积神经网络中的无监督学习。在这些网络中学习的目标是发现音频事件检测和自动语音识别的新特征。该项目的第二部分调查了在内核机器中进行深度学习的可能性。最近发现的一系列核函数模拟了大型多层网络中的计算，表明了这种可能性。该项目的研究部分与其教育活动紧密结合。该项目支持两名研究生，其中包括一名女学生。一个重要的目标是开发公开可用的软件，供其他研究人员使用。