Robust model for speaker verification against session-dependent utterance variation
Robust model for speaker verification against session-dependent utterance variation
复制标题
针对与会话相关的话语变化进行说话者验证的鲁棒模型
DOI：
10.1109/icassp.1998.674381
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
K. Aikawa
中科院分区：
文献类型：
--
作者：
T. Matsui;K. Aikawa
本文研究了一种创建说话人模型的新方法，该模型对基于连续分布隐马尔可夫模型的说话人验证中的话语变化具有鲁棒性。在此方法中，通过将会话到会话的话语变化分别建模为两种不同的变化来估计每个说话者的会话无关特征的分布：一种与会话相关，另一种与会话无关。在实践中，基于说话人自适应训练算法来执行会话相关的话语变化的联合归一化和说话人模型参数的估计。由此产生的说话人模型更准确地表示与会话无关的说话人特征，并且这些模型的辨别能力增加。在使用 20 位说话人在 16 个月内 7 个会话中说出的数据进行的与文本无关的说话人验证实验中，我们表明所提出的方法实现了错误率降低 15%。
This paper investigates a new method for creating speaker models that are robust against utterance variation in continuous distribution hidden Markov model-based speaker verification. In this method, the distribution of the session-independent features for each speaker is estimated by separately modeling the session-to-session utterance variation as two distinct variations: one session-dependent and the other session-independent. In practice, joint normalization of the session-dependent utterance variation and estimation of the parameters of speaker models is performed based on a speaker adaptive training algorithm. The resulting speaker models more accurately represent session-independent speaker characteristics, and the discriminatory capabilities of these models increases. In text-independent speaker verification experiments using data uttered by 20 speakers in 7 sessions over 16 months, we show that the proposed method achieves a 15% reduction in the error rate.