Chronset: An automated tool for detecting speech onset.

Chronset: An automated tool for detecting speech onset.
复制标题

DOI:
10.3758/s13428-016-0830-1
复制
发表时间:
2017-10
影响因子:
5.4
通讯作者:
Carreiras M
Carreiras M
中科院分区:
心理学2区
文献类型:
--
作者:
Roux F;Armstrong BC;Carreiras M

文献摘要

参考文献

被引文献

相似文献

言语起始时间的分析在实验心理学中有着悠久的传统,作为刺激如何影响口语反应的衡量标准。然而,缺乏精确的自动方法来测量这种影响,迫使研究人员依赖于时间密集的手动或半自动技术。在这里,我们提出了Chronset,一个完全自动化的工具,估计语音发作的基础上,通过multitaper频谱分析提取的多个声学特征。使用统计优化技术,我们表明,本方法概括了不同的语言和扬声器人群,它提取的语音发作lavelets,同意密切与人类的观察。最后,我们展示了如何将本方法与以前的工作(Jansen & Watter Behavior Research Methods,40:744-751)相结合,以进一步提高发病检测的精度。Chronset可在www.bcbl.eu/databases/chronset上公开获取。本文的在线版本(doi:10.3758/s13428-016-0830-1)包含补充材料,可供授权用户使用。
The analysis of speech onset times has a longstanding tradition in experimental psychology as a measure of how a stimulus influences a spoken response. Yet the lack of accurate automatic methods to measure such effects forces researchers to rely on time-intensive manual or semiautomatic techniques. Here we present Chronset, a fully automated tool that estimates speech onset on the basis of multiple acoustic features extracted via multitaper spectral analysis. Using statistical optimization techniques, we show that the present approach generalizes across different languages and speaker populations, and that it extracts speech onset latencies that agree closely with those from human observations. Finally, we show how the present approach can be integrated with previous work (Jansen & Watter Behavior Research Methods, 40:744–751,) to further improve the precision of onset detection. Chronset is publicly available online at www.bcbl.eu/databases/chronset. The online version of this article (doi:10.3758/s13428-016-0830-1) contains supplementary material, which is available to authorized users.
DOI: 10.1016/j.neucom.2015.04.025
发表时间: 2015-10-20
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Armstrong, Blair C.;Ruiz-Blondet, Maria V.;Laszlo, Sarah
通讯作者: Laszlo, Sarah
DOI: 10.1037/0096-1523.25.2.361
发表时间: 1999-04-01
影响因子: 2.1
作者:
Kawamoto, AH;Kello, CT
通讯作者: Kello, CT
DOI: 10.3758/bf03200668
发表时间: 1998-08-01
期刊: BEHAVIOR RESEARCH METHODS INSTRUMENTS & COMPUTERS
影响因子: --
作者:
Kello, CT;Kawamoto, AH
通讯作者: Kawamoto, AH
DOI: 10.1006/jmla.2001.2835
发表时间: 2002-07-01
影响因子: 4.3
作者:
Kessler, B;Treiman, R;Mullennix, J
通讯作者: Mullennix, J
DOI: 10.1121/1.4809770
发表时间: 2013-07-01
影响因子: 2.4
作者:
Kim, Dong Kook;Shin, Jong Won;Chang, Joon-Hyuk
通讯作者: Chang, Joon-Hyuk