Investigations on inter-speaker variability in the feature space
Investigations on inter-speaker variability in the feature space
复制标题
特征空间中说话者间变异性的研究
DOI：
--
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
Reinhold Häb
中科院分区：
文献类型：
--
作者：
Reinhold Häb
我们使用Fisher变量分析来衡量说话人归一化技术的有效性。跟踪标准测量不同音素引起的变化与不同说话者造成的变化的比率，作为对特征集的第一次评估，而不需要识别实验。利用这一度量和识别实验，我们证明了倒谱均值归一化除了具有众所周知的通道归一化效应外，还具有说话人归一化效应。同样，声道归一化(VTN)被证明可以消除说话人之间的可变性。对于VTN，我们表明基于每个句子的归一化比基于每个说话人的归一化性能更好。识别结果显示在《华尔街日报》和Hub-4数据库上。
We apply Fisher variate analysis to measure the effectiveness of speaker normalization techniques. A trace criterion, which measures the ratio of the variations due to different phonemes compared to variations due to different speakers, serves as a first assessment of a feature set without the need for recognition experiments. By using this measure and by recognition experiments we demonstrate that cepstral mean normalization also has a speaker normalization effect, in addition to the well-known channel normalization effect. Similarly vocal tract normalization (VTN) is shown to remove inter-speaker variability. For VTN we show that normalization on a per sentence basis performs better than normalization on a per speaker basis. Recognition results are given on Wall Street Journal and Hub-4 databases.