To address the problem that traditional artificial recognition of oral English in the development of oral English is easy to be affected by its own factors leading to the recognition accuracy is not high, this article adopted the long short-term memory (LSTM) neural network in machine learning algorithms to construct a speech recognition model. Pre-emphasis, framing, windowing, Mel Frequency Cepstral Coefficient (MCFF) feature extraction and other preprocessing operations were performed on the speech data. Using MFCC parameters as model inputs to analyze and validate the performance of speech recognition models, multiple parameters such as intonation, speaking speed, and rhythm were utilized to evaluate oral speech. The findings showed that the model constructed in this article achieved a speech recognition accuracy of 95.21%, which can effectively enhance the accuracy of speech recognition.
PutraETeknologiINopemberS. The importance of learning English nowadays. Jurnal Institute of Technology Sepuluh November at Surabaya, 2020.
2.
RustamovITMamaziyayevZX. Development of speaking comprehension in teaching foreign language for professional purposes. Asian J Res Soc Sci Humanit2022; 12(2): 227–233.
3.
PenningtonMCRogerson-RevellP. English pronunciation teaching and research. Research and Practice in Applied Linguistics. Palgrave Macmillan: Springer, 2019.
4.
ZhangCLuY. Study on artificial intelligence: the state of the art and future prospects. Journal of Industrial Information Integration2021; 23: 100224.
5.
XuYLiuXCaoX, et al.Artificial intelligence: a powerful paradigm for scientific research. Innovation2021; 2(4): 100179.
6.
ChenXZouDXieHR, et al.Twenty-five years of computer-assisted language learning: a topic modeling analysis. 2021.
7.
NazeerISonamSSadiaS. The impact of computer-assisted language learning on second language acquisition. Russian Law J2023; 11(4): 27–38.
8.
KumarTRajestSSVillalba-CondoriKO, et al.An evaluation on speech recognition technology based on machine learning. Webology2022; 19(1): 646–663.
9.
ShadievRLiuJ. Review of research on applications of speech recognition technology to assist language learning. ReCALL2023; 35(1): 74–88.
10.
NassifABShahinIAttiliI, et al.Speech recognition using deep neural networks: a systematic review. IEEE Access2019; 7: 19143–19165.
11.
WangDWangXLvS. An overview of end-to-end automatic speech recognition. Symmetry2019; 11(8): 1018.
12.
KholisA. Elsa speak app: automatic speech recognition (ASR) for supplementing English pronunciation skills. Pedagogy: J Eng Lang Teach2021; 9(1): 01–14.
13.
OtterDWMedinaJRKalitaJK. A survey of the usages of deep learning for natural language processing. IEEE Trans Neural Netw Learn Syst2020; 32(2): 604–624.
14.
SunZAnbarasanMPraveen KumarD. Design of online intelligent English teaching platform based on artificial intelligence techniques. Comput Intell2021; 37(3): 1166–1180.
15.
AsrifanAZitaCTVargheeseKJ, et al.The effects of call (computer assisted language learning) toward the students’ English achievement and attitude. J Adv Eng Stud2020; 3(2): 94–106.
16.
AliakbariMMardaniM. Mobile-assisted language learning and its effects on learners’ speaking development. Educ Res Inter2022; 2022(2): 1–14.
17.
BibauwSFrançoisTDesmetP. Discussing with a computer to practice a foreign language: research synthesis and conceptual framework of dialogue-based CALL. Comput Assist Lang Learn2019; 32(8): 827–877.
18.
HuangXZouDChengG, et al.Trends, research issues and applications of artificial intelligence in language education. Educ Technol Soc2023; 26(1): 112–131.
19.
MishraPBiancolilloARogerJM, et al.New data preprocessing trends based on ensemble of multiple preprocessing techniques. TrAC, Trends Anal Chem2020; 132: 116045.
20.
RanjanRThakurA. Analysis of feature extraction techniques for speech recognition system. Int J Innov Technol Explor Eng2019; 8(7C2): 197–200.
21.
KacurJPuterkaBPavlovicovaJ, et al.On the speech properties and feature extraction methods in speech emotion recognition. Sensors2021; 21(5): 1888.
22.
HajarolasvadiNDemirelH. 3D CNN-based speech emotion recognition using k-means clustering and spectrograms. Entropy2019; 21(5): 479.
23.
LokeshSDeviMR. Speech recognition system using enhanced Mel frequency cepstral coefficient with windowing and framing method. Clust Comput2019; 22(Suppl 5): 11669–11679.
24.
JwoDJChangWYWuIH. Windowing techniques, the welch method for improvement of power spectrum estimation. Comput Mater Contin2021; 67(3): 3983–4003.
25.
ZhangTShaoYWuY, et al.An overview of speech endpoint detection algorithms. Appl Acoust2020; 160: 107133.
26.
ZhuCXinLI. Speech endpoint detection method based on LMS noise reduction and improved dual-threshold. J Syst Simul2020; 29(9): 1950–1960.
27.
ArpithaYMadhumathiGLBalajiN. Spectrogram analysis of ECG signal and classification efficiency using MFCC feature extraction technique. J Ambient Intell Hum Comput2022; 13(2): 757–767.
28.
RiyaniAA. Identifying human voice signals using the fast Fourier transform (Fft) method based on Matlab. J Informatics Inform Sys Soft Engine App (INISTA)2019; 1(2): 42–50.
29.
MuralishankarRGhoshDGurugopinathS. A novel modified Mel-DCT filter bank structure with application to voice activity detection. IEEE Signal Process Lett2020; 27: 1240–1244.
30.
ShewalkarANyavanandiDLudwigSA. Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU. J Artif Intell Soft Comput Res2019; 9(4): 235–245.
31.
SherstinskyA. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys Nonlinear Phenom2020; 404: 132306.
32.
JaisIKMIsmailARNisaSQ. Adam optimization algorithm for wide and deep neural network. Knowl Eng Data Sci2019; 2(1): 41–46.
