Semi-supervised speaker identification under covariate shift
Semi-supervised speaker identification under covariate shift
复制标题
DOI：
10.1016/j.sigpro.2009.06.001
复制
发表时间：
2010-08
期刊：
影响因子：
--
通讯作者：
M. Yamada;Masashi Sugiyama;T. Matsui
中科院分区：
文献类型：
--
作者：
M. Yamada;Masashi Sugiyama;T. Matsui
在本文中，我们提出了一种新的半监督说话人识别方法，可以减轻非平稳性的影响，如会话相关的变化，录音环境的变化，和物理条件/情绪。我们假设语音质量变量遵循协变量移位模型，其中只有语音特征分布在训练和测试阶段发生变化。我们的方法包括加权版本的核逻辑回归和交叉验证，并从理论上证明有能力减轻协变量移位的影响。我们的实验表明，通过文本无关/依赖的说话人识别模拟，该方法是有前途的处理语音质量的变化。
In this paper, we propose a novel semi-supervised speaker identification method that can alleviate the influence of non-stationarity such as session dependent variation, the recording environment change, and physical conditions/emotions. We assume that the voice quality variants follow the covariate shift model, where only the voice feature distribution changes in the training and test phases. Our method consists of weighted versions of kernel logistic regression and cross validation and is theoretically shown to have the capability of alleviating the influence of covariate shift. We experimentally show through text-independent/dependent speaker identification simulations that the proposed method is promising in dealing with variations in voice quality.