Binary-Pair Partitioned Neural Networks for Speaker and Dialect Recognition

用于说话人和方言识别的二元对分区神经网络

• 批准号: 9217436
• 负责人: Stephen Zahorian
• 金额: $ 27.24万
• 依托单位: Old Dominion University Research Foundation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-02-15 至 1996-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9217436&HistoricalAwards=false
• 关键词: Binary; Pair; Partitioned; Neural; Networks

9217436 Zahorian This is the second year funding of a two year continuing award. This project investigates the use of the binary-pair partitioning (BPP) method, which partitions an N-way classification task with N*(N-1)/2 pair-discrimination classifiers, in the problem of speaker and dialect identification. The complexity of the BPP networks grows with N2 and the method, which has been examined in a preliminary way for speaker identification, is well suited for cases where the talker identification task involves a large number of speakers (N100). The preliminary studies of speaker identification with the BPP method involved 100 male speakers belonging to three dialect regions of the DARPA/TIMIT database. The system performed with 100% accuracy in a text independent than results reported in the literature for similar tasks. The BPP approach is also suited for tasks where multiple elemental decisions can be combined to obtain an overall decision, such as dialect or language identification. Refinements and extensions to the method will be investigated, such as (1) enhancement of the input features, (2) the effects of noise and channel distortion on performance, (3) performance in a speaker verification mode as well as in an identification mode, (4) performance in sex and dialect identification, (5) improvements that this method may provide for speech recognition, and (6) training of BPP networks to minimize the probability of error rather than the mean square error.

9217436扎哈里安今年是两年持续奖的第二年资金来源。该项目研究了二进制对划分(BPP)方法在说话人和方言识别问题中的应用，该方法使用N*(N-1)/2对区分分类器来划分N-路分类任务。BPP网络的复杂性随着N2的增加而增加，并且该方法非常适合于说话者识别任务涉及大量说话者(N100)的情况，并且该方法已经被初步检验用于说话人识别。使用BPP方法对100名男性说话人进行了初步研究，这些人来自DARPA/TIMIT数据库的三个方言区域。与文献中报告的类似任务的结果相比，该系统在独立于文本的文本中执行100%的准确率。BPP方法还适用于可以组合多个基本决策以获得总体决策的任务，例如方言或语言识别。将研究对该方法的改进和扩展，例如(1)输入特征的增强，(2)噪声和信道失真对性能的影响，(3)在说话人验证模式和识别模式中的性能，(4)在性别和方言识别方面的性能，(5)该方法可以为语音识别提供的改进，以及(6)训练BPP网络以最小化错误概率而不是均方误差。