Dynamic Feature Extraction Method of Phone Speakers Based on Deep Learning

Background: Nowadays, speech recognition has become one of the important technologies for human-computer interaction. Speech recognition is essentially a process of speech training and pattern recognition, which makes feature extraction technology particularly essential. The quality of feature extraction is directly related to the accuracy of speech recognition. Dynamic feature parameters can effectively improve the accuracy of speech recognition. These parameters make the speech dynamic feature extraction to have a higher research value. The traditional dynamic feature extraction method is easier to generate more redundant information, resulting in low recognition accuracy. Methods: Therefore, based on a new speech feature extraction method, which is based on deep learning for speech feature extraction, is proposed in the present study. Firstly, the speech signal is preprocessed by pre-emphasis, windowing, filtering, and endpoint detection. Then, the Sliding Differential Cepstral (SDC) feature is extracted, which contains the voice information of the front and back frames. Finally, the feature is used as input to extract the dynamic features that represent the depth essence of speech information through the deep self-encoding neural network. Results: The simulation results show that the dynamic features extracted by in-depth learning have better recognition performance than the original features, and have a good effect on speech recognition.