Analysis and Calibration of Lombard Effect and Whisper for Speaker Recognition.

Analysis and Calibration of Lombard Effect and Whisper for Speaker Recognition.
复制标题

DOI:
10.1109/taslp.2021.3053388
复制
发表时间:
2021
影响因子:
5.4
通讯作者:
Hansen, John H. L.
Hansen, John H. L.
中科院分区:
计算机科学2区
文献类型:
--
作者:
Kelly, Finnian;Hansen, John H. L.

文献摘要

参考文献

被引文献

相似文献

声音努力的变化可能会对针对中性语音使用而优化的说话人识别系统造成挑战。朗巴德效应和耳语是两种常见的声音努力变化形式,导致非中性语音,第一种是由于噪声暴露,第二种是由于说话者的故意调整。在这篇文章中,使用多个Lombard效应和耳语语料库的非中性条件下的说话人识别性能的比较评估。这些声乐努力的歧视和校准性能的不利影响,全球,每语料库,每扬声器的水平探索使用传统的错误度量,沿着与模型和分数空间的视觉表示。随后引入非中性语音检测器,并以多种方式用于通知分数校准。提出了两种校准方法,并表明它们可以将误差降低到与依赖地面真实声音努力信息的最佳校准方法相同的水平。本文提供了一种可推广的方法来检测发声努力的变化,并利用这些知识来通知和推进说话人识别系统的行为。
Variations in vocal effort can create challenges for speaker recognition systems that are optimized for use with neutral speech. The Lombard effect and whisper are two commonly-occurring forms of vocal effort variation that result in non-neutral speech, the first due to noise exposure and the second due to intentional adjustment on the part of the speaker. In this article, a comparative evaluation of speaker recognition performance in non-neutral conditions is presented using multiple Lombard effect and whisper corpora. The detrimental impact of these vocal effort variations on discrimination and calibration performance on global, per-corpus, and per-speaker levels is explored using conventional error metrics, along with visual representations of the model and score spaces. A non-neutral speech detector is subsequently introduced and used to inform score calibration in several ways. Two calibration approaches are proposed and shown to reduce error to the same level as an optimal calibration approach that relies on ground-truth vocal effort information. This article contributes a generalizable methodology towards detecting vocal effort variation and using this knowledge to inform and advance speaker recognition system behavior.
DOI: 10.1016/j.engappai.2014.05.003
发表时间: 2014-09-01
影响因子: 8
作者:
Bahari, Mohamad Hasan;McLaren, Mitchell;van Leeuwen, David A.
通讯作者: van Leeuwen, David A.
DOI: 10.1109/taslp.2018.2875794
发表时间: 2019-01-01
影响因子: 5.4
作者:
Ferrer, Luciana;Nandwana, Mahesh Kumar;Lawson, Aaron
通讯作者: Lawson, Aaron
DOI: 10.1007/s10772-017-9461-x
发表时间: 2017-12-01
影响因子: --
作者:
Ghaffarzadegan, Shabnam;Boril, Hynek;Hansen, John H. L.
通讯作者: Hansen, John H. L.
DOI: 10.1121/1.5042758
发表时间: 2018-06-01
影响因子: 2.4
作者:
Alghamdi, Najwa;Maddock, Steve;Brown, Guy J.
通讯作者: Brown, Guy J.
DOI: 10.1109/tasl.2010.2091631
发表时间: 2011-07-01
影响因子: --
作者:
Fan, Xing;Hansen, John H. L.
通讯作者: Hansen, John H. L.