Implementation of noise reduction optimization process of language lab recording based on RNN model

Yuzhu Zhang, Wei Zeng, Qiang Liao

Abstract


Speech signal noise reduction involves speech signal processing technology, which is one of the core technologies in the
field of information application. Speech signal optimization analysis and processing is also a popular direction in the field of artificial
intelligence. In this paper, a speech signal optimization processing method based on the recurrent neural network RNN model is proposed for
the language laboratory recording signal as the research object. The key technologies in the fi eld of deep learning are introduced for audio
noise reduction processing. By using experimental simulation, the signal-to-noise ratio of the recording signal is improved, so as to obtain a
more ideal language laboratory recording audio fi le.

Keywords


Speech signal; Deep learning; Recurrent neural network RNN ; S ignal-to-noise ratio

Full Text:

PDF

Included Database


References


[1] Ma C, Li D, Jia X. Optimal scale-invariant signal-to-noise ratio and curriculum learning for monaural multi-speaker speech separation in noisy

environment[C]//2020 Asia-Pacifi c Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2020: 711-715.

[2] Luo Y, Mesgarani N. Tasnet: time-domain audio separation network for real-time, single-channel speech separation[C]//2018 IEEE International

Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018: 696-700.

[3] Jiang Kaiyu. Research on Correlation Analysis of Audio Noise Reduction [D]. University of Chinese Academy of Sciences,2014.

[4] Han Changjun. Application of Speech Signal Denoising Method Based on MATLAB [J]. Journal of Liaodong University (Natural Science

Edition),2017,24(01):72-77.

[5] Jin Zequn. Abnormal Audio Detection Method Based on Deep Learning [D]. Shenyang Jianzhu University,2019.




DOI: https://doi.org/10.18686/esta.v10i2.394

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Yuzhu Zhang,Wei Zeng,Qiang Liao