A Study of Teaching Quality Improvement in English Listening Teaching in the Context of Speech Recognition Technology

At present, most English learners spend much less time listening to English than reading it.Most of the language knowledge is acquired through visual channels rather than auditory channels, thus the language knowledge does not form corresponding auditory images in the mind, so the phenomenon of reading but not understanding occurs.Aiming at this kind of problem, this paper tries to explore the role of speech recognition in improving the quality of English teaching by combining it with this technology.The article first recognizes English spoken speech features based on Mel's frequency cepstrum feature parameters and deep belief network, then expands the number of speech features from both time and frequency by means of distortion and masking, and designs the encoder part by combining 2D convolutional neural networks and GRUs, and finally models the local and temporal information in the speech features to realize the recognition of English speech.And thus establish a new model of English listening teaching.As verified by the dataset, the method in this paper can accurately recognize speech features of different emotions, and the recognition effect is better than other models of the same type.In addition, an equivalence study between the proposed teaching model and the traditional teaching model was conducted with 70 foreign students in a university.It was found that the mean value of the total scores of the candidates in the group of the teaching model proposed in this paper was 0.26 points higher than the mean value of the total scores of the candidates in the traditional group, among which, the mean value of the listening scores of the candidates in the group of the teaching model proposed in this paper was 0.1 points higher than the mean value of the listening scores of the candidates in the traditional group.