Coupling of Bottom-Up and Top-Down Knowledge Sources for Automatic Speech Recognition

这笔赠款将支持几种技术的研究， 对要在扬声器中使用的声学语音信息进行编码， 独立连续语音识别。 时滞和 递归神经网络架构将用于频谱 分析重叠的语音段，与 语音的贝叶斯最大似然分类 光谱动力学 神经网络输出将被编码 作为近似的语音距离，具有两级迭代 优化整体识别的训练方法。 一体化 这个系统与隐藏马尔可夫语音识别也将 研究了

This grant will support research in several techniques for encoding acoustic-phonetic information to be used in speaker- independent continuous-speech recognition. Time-delay and recursive neural network architectures will be used for spectral analysis of overlapping speech segments, to be compared with a Bayesian maximum-likelihood classification of the speech spectral dynamics. Neural-network outputs will then be encoded as approximate phonetic distances, with a two-level iterative training method to optimize overall recognition. Integration of this system with hidden-Markov speech recognition will also be studied.