Evaluating Low-Level Speech Features Against Human Perceptual Data

Evaluating Low-Level Speech Features Against Human Perceptual Data
复制标题

根据人类感知数据评估低级语音特征

DOI:
10.1162/tacl_a_00071
复制
发表时间:
2017
影响因子:
10.9
通讯作者:
Jansen, Aren
Jansen, Aren
中科院分区:
人文科学1区
文献类型:
--
作者:
Richter, Caitlin;Feldman, Naomi H.;Salgado, Harini;Jansen, Aren

文献摘要

参考文献

被引文献

相似文献

我们介绍了一种测量低电平语音之间的对应关系的方法, 特征和人类感知,使用语音感知的认知模型 直接在语音记录上实现。我们评估两个说话人归一化 技术使用这种方法,并发现在这两种情况下,语音特征, 在说话者之间进行归一化比未归一化更好地预测人类数据 语音特征,与以前的研究一致。结果进一步显示, 不同的标准化方法在预测人类数据方面存在差异。 这项工作提供了一个新的框架,评估低层次的代表性, 他们的演讲与人类的感知相匹配,并为创建奠定了基础 更生态有效的言语感知模型。
We introduce a method for measuring the correspondence between low-level speech features and human perception, using a cognitive model of speech perception implemented directly on speech recordings. We evaluate two speaker normalization techniques using this method and find that in both cases, speech features that are normalized across speakers predict human data better than unnormalized speech features, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a new framework for evaluating low-level representations of speech on their match to human perception, and lays the groundwork for creating more ecologically valid models of speech perception.
特征空间中说话者间变异性的研究
DOI: --
发表时间: 1999
期刊: 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
影响因子: --
作者:
Reinhold Häb
通讯作者: Reinhold Häb
DOI: 10.1037/a0022325
发表时间: 2011-04
影响因子: 5.4
作者:
McMurray, Bob;Jongman, Allard
通讯作者: Jongman, Allard
DOI: 10.1016/j.wocn.2005.08.004
发表时间: 2006-10-01
影响因子: 1.9
作者:
Johnson, Keith
通讯作者: Johnson, Keith
DOI: 10.1162/0898929054985473
发表时间: 2005-09-01
影响因子: 3.2
作者:
Blumstein, SE;Myers, EB;Rissman, J
通讯作者: Rissman, J
DOI: 10.1121/1.2024119
发表时间: 1989
期刊: The Journal of the Acoustical Society of America
影响因子: --
作者:
James D. Miller
通讯作者: James D. Miller