FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-120144

Research Article |

Speech Enhancement with Background Noise Suppression in Various Data Corpus Using Bi-LSTM Algorithm

Author(s): Vinothkumar G* and Manoj Kumar D

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 12, Issue 1

Publisher : FOREX Publication

Published : 28 march 2024

e-ISSN : 2347-470X

Page(s) : 322-328

DOI: https://doi.org/10.37391/IJEER.120144

Abstract

Noise reduction is one of the crucial procedures in today’s teleconferencing scenarios. The signal-to-noise ratio (SNR) is a paramount factor considered for reducing the Bit error rate (BER). Minimizing the BER will result in the increase of SNR which improves the reliability and performance of the communication system. The microphone is the primary audio input device that captures the input signal, as the input signal is carried away it gets interfered with white noise and phase noise. Thus, the output signal is the combination of the input signal and reverberation noise. Our idea is to minimize the interfering noise thus improving the SNR. To achieve this, we develop a real-time speech-enhancing method that utilizes an enhanced recurrent neural network with Bidirectional Long Short Term Memory (Bi-LSTM). One LSTM in this sequence processing framework accepts the input in the forward direction, whereas the other LSTM takes it in the opposite direction, making up the Bi-LSTM. Considering Bi-LSTM, it takes fewer tensor operations which makes it quicker and more efficient. The Bi-LSTM is trained in real-time using various noise signals. The trained system is utilized to provide an unaltered signal by reducing the noise signal, thus making the proposed system comparable to other noise-suppressing systems. The STOI and PESQ metrics demonstrate a rise of approximately 0.5% to 14.8% and 1.77% to 29.8%, respectively, in contrast to the existing algorithms across various sound types and different input signal-to-noise ratio (SNR) levels.

Keywords: RNN, Bi-LSTM, SNR, Speech Enhancement, Background Noise, DNN.




Vinothkumar G*, Research Scholar, Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, Tamil Nadu, India; Email: vinothkg@srmist.edu.in

Manoj Kumar D, Assistant Professor, Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, Tamil Nadu, India; Email: manojkud1@srmist.edu.in

    [1] Loizou, P.C. Speech Enhancement: Theory and Practice; CRC Press: New York, NY, USA, 2013.
    [2] Xu, Yong, et al. "A regression approach to speech enhancement based on deep neural networks." IEEE/ACM Transactions on Audio, Speech, and Language Processing 23.1 (2014): 7-19. [CrossRef]
    [3] Kumar, Anurag, and Dinei Florencio. "Speech enhancement in multiple-noise conditions using deep neural networks." arXiv preprint arXiv:1605.02427 (2016). [CrossRef]
    [4] Park, Se Rim, and Jinwon Lee. "A fully convolutional neural network for speech enhancement." arXiv preprint arXiv:1609.07132 (2016). [CrossRef]
    [5] Pandey, Ashutosh, and DeLiang Wang. "TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain." ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019. [CrossRef]
    [6] Jannu, Chaitanya, and Sunny Dayal Vanambathina. "An Overview of Speech Enhancement Based on Deep Learning Techniques." International Journal of Image and Graphics (2023): 2550001. [CrossRef]
    [7] Schroter, Hendrik, et al. "Low latency speech enhancement for hearing aids using deep filtering." IEEE/ACM Transactions on Audio, Speech, and Language Processing 30 (2022): 2716-2728. [CrossRef]
    [8] Hepsiba, D., R. Vinotha, and L. D. Vijay Anand. "Speech Enhancement and Recognition Using Deep Learning Algorithms: A Review." Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2022 (2023): 259-268. [CrossRef]
    [9] Peracha, Fahad Khalil, et al. "Causal speech enhancement using dynamical-weighted loss and attention encoder-decoder recurrent neural network." Plos one 18.5 (2023): e0285629. [CrossRef]
    [10] Huang, Ping, and Yafeng Wu. "Teacher-Student Training Approach Using an Adaptive Gain Mask for LSTM-Based Speech Enhancement in the Airborne Noise Environment." Chinese Journal of Electronics 32.4 (2023): 882-895. [CrossRef]
    [11] Pandey, Ashutosh, and DeLiang Wang. "Self-attending RNN for speech enhancement to improve cross-corpus generalization." IEEE/ACM Transactions on Audio, Speech, and Language Processing 30 (2022): 1374-1385. [CrossRef]
    [12] Shukla, Vasundhara, and Preety D. Swami. "Sparse Signal Recovery through Long Short-Term Memory Networks for Compressive Sensing-Based Speech Enhancement." Electronics 12.14 (2023): 3097. [CrossRef]
    [13] Saleem, Nasir, et al. "Deepresgru: residual gated recurrent neural network-augmented kalman filtering for speech enhancement and recognition." Knowledge-Based Systems 238 (2022): 107914. [CrossRef]
    [14] Yu, Meng, et al. "NeuralEcho: A self-attentive recurrent neural network for unified acoustic echo suppression and speech enhancement." arXiv preprint arXiv:2205.10401 (2022).
    [15] G. Vinothkumar and P. Phani Kumar Polasi “Filter performance of sparse noise for controlling the occurrence of noise-induced hearing loss using hybrid algorithm “ AIP Conference Proceedings 2405, 030013 (2022); https://doi.org/10.1063/5.0072454 Published Online: 05 April 2022. [CrossRef]
    [16] Hasannezhad, Mojtaba, et al. "An integrated CNN-LSTM framework for complex ratio mask estimation in speech enhancement." 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2020. [CrossRef]
    [17] Song, Zhendong, et al. "Hybrid dilated and recursive recurrent convolution network for time-domain speech enhancement." Applied Sciences 12.7 (2022): 3461. [CrossRef]
    [18] Wang, Youming, et al. "Speech enhancement from fused features based on deep neural network and LSTM network." EURASIP Journal on Advances in Signal Processing 2021 (2021): 1-19. [CrossRef]
    [19] Abdulbaqi, Jalal, et al. "Residual recurrent neural network for speech enhancement." ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020. [CrossRef]
    [20] Vuong, Tyler, Yangyang Xia, and Richard M. Stern. "A modulation-domain loss for neural-network-based real-time speech enhancement." ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021. [CrossRef]
    [21] Hasannezhad, Mojtaba, et al. "PACDNN: A phase-aware composite deep neural network for speech enhancement." Speech Communication 136 (2022): 1-13. [CrossRef]
    [22] Cui, Xingyue, Zhe Chen, and Fuliang Yin. "Speech enhancement based on simple recurrent unit network." Applied Acoustics 157 (2020): 107019. [CrossRef]
    [23] Abdulbaqi, Jalal, Yue Gu, and Ivan Marsic. "RHR-Net: A residual hourglass recurrent neural network for speech enhancement." arXiv preprint arXiv:1904.07294 (2019). [CrossRef]
    [24] Peng, Kaibei, et al. "A Speech Enhancement Method Using Attention Mechanism and LSTM." 2021 3rd International Conference on Industrial Artificial Intelligence (IAI). IEEE, 2021. [CrossRef]
    [25] Valin, Jean-Marc. "A hybrid DSP/deep learning approach to real-time full-band speech enhancement." 2018 IEEE 20th international workshop on multimedia signal processing (MMSP). IEEE, 2018. [CrossRef]

Vinothkumar G and Manoj Kumar D (2024), Speech Enhancement with Background Noise Suppression in Various Data Corpus Using Bi-LSTM Algorithm. IJEER 12(1), 322-328. DOI: 10.37391/IJEER.120144.