A study on minimum error discriminative training for speaker recognition
A study on minimum error discriminative training for speaker recognition
复制标题
说话人识别最小误差判别训练研究
DOI：
10.1121/1.412286
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
A. Rosenberg
中科院分区：
文献类型：
--
作者：
Chi;Chin;W. Chou;B. Juang;A. Rosenberg
研究了利用区分训练来构造说话人的隐马尔可夫模型进行验证和辨认的方法。与仅基于同一说话人的训练话语来估计说话人模型的传统最大似然训练不同，使用了一种区分训练方法，该方法考虑了其他竞争说话人的模型，并制定了优化准则，从而增强了说话人分离，并直接最小化了训练数据上的说话人识别错误率。利用概率下降算法得到最优解。对于所有的实验，都使用了一个由100名说话者组成的孤立的数字数据库。对于说话人识别，所得到的辨别说话人模型比使用传统训练算法获得的识别错误率降低了25%以上。提出了一种新的归一化得分函数，使验证公式与最小误差保持一致。
The use of discriminative training to construct hidden Markov models of speakers for verification and identification is studied. As opposed to conventional maximum likelihood training which estimates a speaker’s model based only on the training utterances from the same speaker, a discriminative training approach is used which takes into account the models of other competing speakers and formulates the optimization criterion such that speaker separation is enhanced and speaker recognition error rate on the training data is directly minimized. The optimization solution is obtained with a probabilistic descent algorithm. For all experiments an isolated digit database consisting of 100 speakers is used. For speaker identification, the resulting discriminative speaker models reduce the identification error rate by more than 25% over the results obtained with the conventional training algorithm. A new normalized score function is proposed which makes the verification formulation consistent with the minimum erro...