Noise-robust automatic speech recognition using a predictive echo state network
Noise-robust automatic speech recognition using a predictive echo state network
复制标题
DOI：
10.1109/tasl.2007.896669
复制
发表时间：
2007-07-01
影响因子：
--
通讯作者：
Harris, John G.
中科院分区：
文献类型：
--
作者：
Skowronski, Mark D.;Harris, John G.
人工神经网络已被证明在自动语音识别(ASR)任务中表现良好，尽管其复杂性和过高的计算成本限制了它们的使用。最近，Jaeger引入了一种训练简单的递归神经网络--回声状态网络(ESN)，并在时间序列预测实验中显示出优于传统方法的性能。我们通过将ESN与状态机框架相结合来创建预测性ESN分类器。在小词汇量的ASR实验中，我们比较了预测ESN分类器和隐马尔可夫模型(HMM)的抗噪性能随模型大小和信噪比的变化。预测ESN分类器的性能比HMM高出8dBSNR，并且对于每个状态具有更多状态和更少核的体系结构，两种模型都获得了最大的抗噪精度。使用训练/验证/测试说话人的随机集合的十次试验，预测ESN分类器的准确率为81+/-3%，而HMM的准确率为61+/-2%，平均在0到20dBSNR之间。ESN的闭式回归训练显著降低了网络的计算成本，ESN的储存库创建了具有记忆的输入的高维表示，从而提高了抗噪分类能力。
Artificial neural networks have been shown to perform well in automatic speech recognition (ASR) tasks, although their complexity and excessive computational costs have limited their use. Recently, a recurrent neural network with simplified training, the echo state network (ESN), was introduced by Jaeger and shown to outperform conventional methods in time series prediction experiments. We created the predictive ESN classifier by combining the ESN with a state machine framework. In small-vocabulary ASR experiments, we compared the noise-robust performance of the predictive ESN classifier with a hidden Markov model (HMM) as a function of model size and signal-to-noise ratio (SNR). The predictive ESN classifier outperformed an HMM by 8-dB SNR, and both models achieved maximum noise-robust accuracy for architectures with more states and fewer kernels per state. Using ten trials of random sets of training/validation/test speakers, accuracy for the predictive ESN classifier, averaged between 0 and 20 dB SNR, was 81 +/- 3%, compared to 61 +/- 2% for an HMM. The closed-form regression training for the ESN significantly reduced the computational cost of the network, and the reservoir of the ESN created a high-dimensional representation of the input with memory which led to increased noise-robust classification.