Search

In this paper, a CNN-based structure for the time-frequency localization of information is proposed for Persian speech recognition. Research has shown that the receptive fields' spectrotemporal plasticity of some neurons in mammals' primary auditory cortex and midbrain makes localization facilities improve recognition performance. Over the past few years, much work has been done to localize time-frequency information in ASR systems, using the spatial or temporal immutability properties of methods such as HMMs, TDNNs, CNNs, and LSTM-RNNs. However, most of these models have large parameter volumes and are challenging to train. For this purpose, we have presented a structure called Time-Frequency Convolutional Maxout Neural Network (TFCMNN) in which parallel time-domain and frequency-domain 1D-CMNNs are applied simultaneously and independently to the spectrogram, and then their outputs are concatenated and applied jointly to a fully connected Maxout network for classification. To improve the performance of this structure, we have used newly developed methods and models such as Dropout, maxout, and weight normalization. Two sets of experiments were designed and implemented on the FARSDAT dataset to evaluate the performance of this model compared to conventional 1D-CMNN models. According to the experimental results, the average recognition score of TFCMNN models is about 1.6% higher than the average of conventional 1D-CMNN models. In addition, the average training time of the TFCMNN models is about 17 hours lower than the average training time of traditional models. Therefore, as proven in other sources, time-frequency localization in ASR systems increases system accuracy and speeds up the training process.

In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech recognition applications were fully connected Neural Networks (FCNNs) and, consequently, Deep Neural Networks (DNNs). Although these models have better performance compared to GMM / HMM models, they do not have the proper structure to model local speech information. Convolutional Neural Network (CNN) is a good option for modeling the local structure of biological signals, including speech signals. Another issue that Deep Artificial Neural Networks face, is the convergence of networks on training data. The main inhibitor of convergence is the presence of local minima in the process of training. Deep Neural Network Pre-training methods, despite a large amount of computing, are powerful tools for crossing the local minima. But the use of appropriate neuronal models in the network structure seems to be a better solution to this problem. The Rectified Linear Unit neuronal model and the Maxout model are the most suitable neuronal models presented to this date. Several experiments were carried out to evaluate the performance of the methods and structures mentioned. After verifying the proper functioning of these methods, a combination of all models was implemented on FARSDAT speech database for continuous speech recognition. The results obtained from the experiments show that the combined model (CMDNN) improves the performance of ANNs in speech recognition versus the pre-trained fully connected NNs with sigmoid neurons by about 3%., Comment: 6 pages, 2 figures, conference paper submitted to 2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)