Evaluation on unsupervised speaker adaptation based on sufficient HMM statictics of selected speakers
Evaluation on unsupervised speaker adaptation based on sufficient HMM statictics of selected speakers
复制标题
基于所选说话人的充分 HMM 静力学的无监督说话人自适应评估
DOI：
10.21437/eurospeech.2001-317
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
K. Shikano
中科院分区：
文献类型：
--
作者：
Shinichi Yoshizawa;Akira Baba;Kanako Matsunami;Yuichiro Mera;M. Yamada;Akinobu Lee;K. Shikano
本文描述了一种有效的无监督说话人适应方法。该方法基于（1）选择声学上接近测试说话者的说话者子集，以及（2）根据先前存储的所选说话者数据的足够统计数据计算适应的模型参数。在这种方法中，自适应只需要一些无监督测试说话者的数据。此外，通过使用所选说话者数据的足够 HMM 统计数据，可以完成快速适应。与预聚类方法相比，由于聚类结果是根据测试说话人的在线数据确定的，因此该方法可以获得更优化的聚类。实验结果表明，该方法比说话人无关模型的 MLLR 获得了更好的改进。对所提出的方法进行了详细评估和讨论。
This paper describes an efficient method of unsupervised speaker adaptation. This method is based on (1) selecting a subset of speakers who are acoustically close to a test speaker, and (2) calculating adapted model parameters according to the previously stored sufficient statistics of the selected speakers’ data. In this method, only a few unsupervised test speaker’s data are necessary for the adaptation. Also, by using the sufficient HMM statistics of the selected speakers’ data, a quick adaptation can be done. Compared with a pre-clustering method, the proposed method can obtain a more optimal cluster because the clustering result is determined according to test speaker’s data on-line. Experimental results show that the proposed method attains better improvement than MLLR from the speaker-independent model. The proposed method is evaluated in details and discussed.