一种量子神经网络说话人识别方法

针对说话人语音特征空间边界存在模糊性的特点,构建了一种量子神经网络识别分类器,用于说话人识别,以改善存在交叉数据的语音特征参数的分类效果。提出了一种基于人工免疫算法的量子间隔训练方法,以改善传统量子神经网络训练算法的不足。以TIMIT语音库为测试语音,与传统BP网络和基于常规梯度下降量子间隔训练算法的量子神经网络做对比实验。实验证明,算法能有效提高说话人识别系统的识别率,同时与高斯混合模型相比,具有更好的抗噪声性能。

Speaker recognition method based on quantum neural network

To tackle the problem that fuzziness exists in the speech feature space boundary, a speaker recognition model based on quantum neural network (QNN) was constructed to improve the classification performance of speech feature parameters. One method based on the artificial immune algorithm was proposed to the training quantum neural network. The experimental results show that the performance of the proposed method is better than that of the traditional BP neural network and gradient descent training QNN, and also more robust to noise than GMM.