【摘要】 论文提出了一种连续隐Markov模型和BP神经网络相结合的、具有两次辨识过程的抗噪孤立字识别模型 .首先以连续隐Markov模型完成语音信号的时序建模并提供一次识别信息 ;以BP神经网络进行后处理 ,提取二次识别信息 ,识别结果由两次识别信息共同决定 .实验证明 ,由于有效地利用了隐Markov模型的强时序信号处理能力和BP神经网络的强模式分类和泛化性能 ,这种识别模型明显地改善了孤立字识别系统的抗噪性能 .更多还原

【Abstract】 To recognize isolated words in noisy environments, A new robust recognition model with dual recognition procedures based on continuous Hidden Markov Models(CHMM) and BP neural networks(BPNN) is presented. First, the CHMM is applied as the front end to process the time sequence of speech and the primary recognition information is provided in this step. In the next step, BPNN is applied as the back end and because of its superior functions of pattern classification and generalization, the primary recognition information is non linearly mapped into the secondary recognition information. The final recognition procedure is accomplished with the two kinds of recognition information. Experiments prove that using this robust model, recognition rate can be noticeably improved in noisy environments.更多还原