Speaker recognition using syllable-based constraints for cepstral frame selection
Speaker recognition using syllable-based constraints for cepstral frame selection
复制标题
使用基于音节的约束进行倒谱帧选择的说话人识别
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Elizabeth Shriberg
中科院分区：
文献类型：
--
作者：
T. Bocklet;Elizabeth Shriberg
我们描述了一种新的 GMM-UBM 说话人识别系统，该系统使用标准倒谱特征，但为不同的子系统选择不同的语音帧。子系统或“约束”基于音节级信息并在分数级进行组合。针对英语电话列车和测试条件的 NIST 2006 和 2008 测试数据集的结果表明，一组八个约束表现得非常好，比其他常用的倒谱模型具有更好的性能。鉴于可能的约束和组合的世界在很大程度上尚未探索，该方法很可能可以进一步改进。
We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “constraints”, are based on syllable-level information and combined at the score level. Results on both the NIST 2006 and 2008 test data sets for the English telephone train and test condition reveal that a set of eight constraints performs extremely well, resulting in better performance than other commonly-used cepstral models. Given the still largely-unexplored world of possible constraints and combinations, it is likely that the approach can be even further improved.