Academic Journal of Computing & Information Science, 2022, 5(7); doi: 10.25236/AJCIS.2022.050714.
Xirui Wang, Jiachun Wang, Yunqi Cao, Ziyi Ye, Wenlian Zhang
School of Electrical and Electronic Engineering, Shijiazhuang Tiedao University, Shijiazhuang, Hebei, China
Recurrent neural networks, as an effective method to study the analysis and prediction of large-scale time series, have existed in various applications on time series data, but the traditional RNN neural network has the problem of gradient disappearance and the problem of poor prediction accuracy has not been solved. This paper proposes a vocal recognition system based on LSTM neural network, whose core structure can be divided into four parts: forgetting gate, input gate, cell The core structure can be divided into four parts: forgetting gate, input gate, state and output gate, which are more suitable to analyze the characteristics of different human voice patterns, and can obtain higher recognition accuracy after the process of feature extraction, data enhancement, model training and voice pattern recognition. Finally, the performance of the LSTM neural network is tested on 300 speech data, and the test results prove that the LSTM neural network can obtain high recognition rate with less iterations.
LSTM neural network model; RNN neural network; MFCC; Voice recognition
Xirui Wang, Jiachun Wang, Yunqi Cao, Ziyi Ye, Wenlian Zhang. Principle Analysis of Voiceprint Identification and Authentication System Based on LSTM. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 7: 85-89. https://doi.org/10.25236/AJCIS.2022.050714.
[1] Du Kangji. Improved recurrent neural network method and its application research [D]. Northeastern Electric Power University, 2021.
[2] DU Xiaoming, GE Shilun, WANG Nianxin. Academic prediction based on CNN___LSTM hybrid neural network model [J]. Modern Educational Technology, 2021, 31(12): 69-76.
[3] Liu Xiaoxuan, Ji Yi, Liu Chunping. LSTM neural network-based vocal pattern recognition [J]. Computer Science, 2021, 48(S2): 270-274.
[4] Yu Lingfei, Liu Qiang. Research and application of deep recurrent network-based vocal recognition method [J]. Computer Application Research, 2019, 36(01): 153-158.
[5] Liu Y. Research on key technology of vocal pattern recognition based on deep learning [D]. Qingdao University of Science and Technology, 2021