Abstract
Speech enhancement is an important property in today’s world because most applications use voice recognition as an important feature for performing operations in it. Perfect recognition of commands is achieved only by recognizing the voice correctly. Hence, the speech signal must be enhanced and free from background noise for the recognition process. In the existing approach, a recurrent convolutional encoder/decoder is used for denoising the speech signal. It utilized the signal-to-noise ratio property for enhancing the speech signal. It removes the noise signal effectively by having a low character error rate. But it does not describe the range of SNR of the noise added to the signal. Hence, in this, optimized deep learning is proposed to enhance the speech signal. AI function deep learning mimics the human brain's ability to analyze data and create patterns for use in making decisions. An optimized convolutional neural network was proposed for enhancing the speech for a different type of signal-to-noise ratio value of noises. Here, the particle swarm optimization process performs tuning the hyper-parameters of the convolutional neural network. The tuning of value is to minimize the character error rate of the signal. The proposed method is realized using MATLAB R2020b software and evaluation takes place by calculating the character error rate, PESQ, and STOI of the signal. Then, the comparison of the proposed and existing method takes place using evaluation metrics with − 5 dB, 0 dB, + 5 dB and + 10 dB.
Similar content being viewed by others
References
Abdulbaqi, J., Gu, Y., Chen, S., & Marsic, I. (2020). Residual recurrent neural network for speech enhancement. In ICASSP 2020—2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020 (pp. 6659–6663).
Abdulbaqi, J., Gu, Y., & Marsic, I. (2019). RHR-Net: A residual hourglass recurrent neural network for speech enhancement. ArXiv, abs/1904.07294
Bahadur, I., Kumar, S., & Agarwal, P. (2021). Performance measurement of a hybrid speech enhancement technique. International Journal of Speech Technology, 24, 665–677.
Bhat, G. S., Shankar, N., Reddy, C. K. A., & Panahi, I. M. S. (2019). A real-time convolutional neural network based speech enhancement for hearing impaired listeners using smartphone. IEEE Access, 7, 78421–78433.
Borgstrom, B. J., & Brandstein, M. S. (2020). The speech enhancement via attention masking network (SEAMNET): An end-to-end system for joint suppression of noise and reverberation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 515–526.
Chai, L., Du, J., Liu, Q., & Lee, C. (2021). A cross-entropy-guided measure (CEGM) for assessing speech recognition performance and optimizing DNN-based speech enhancement. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 106–117.
Fu, S.-W., Wang, T.-W., Tsao, Y., Lu, X., & Kawai, H. (2018). End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(9), 1570–1584.
Gnanamanickam, J., Natarajan, Y., & SriPreethaa, K. R. (2021). A hybrid speech enhancement algorithm for voice assistance application. Sensors (basel, Switzerland), 21(21), 7025.
Grzywalski, T., & Drgas, S. (2019). Using recurrences in time and frequency within U-Net architecture for speech enhancement. In ICASSP 2019—2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.
Gutiérrez-Muñoz, M., & Coto-Jiménez, M. (2022). An experimental study on speech enhancement based on a combination of wavelets and deep learning. Computation, 10, 102. https://doi.org/10.3390/computation10060102
Hou, J.-C., Wang, S.-S., Lai, Y.-H., Tsao, Y., Chang, H.-W., & Wang, H.-M. (2018). Audio–visual speech enhancement using multimodal deep convolutional neural networks. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(2), 117–128.
Hsieh, T.-A., Wang, H.-M., Lu, X., & Tsao, Y. (2020). WaveCRN: An efficient convolutional recurrent neural network for end-to-end speech enhancement. IEEE Signal Processing Letters, 27, 2149–2153.
Jose, W. J. (2020). AMRConvNet: AMR-coded speech enhancement using convolutional neural networks. In 2020 IEEE international conference on systems, man, and cybernetics (SMC), 2020.
Karthik, A., & Mazher Iqbal, J. L. (2020). Performance estimation based recurrent-convolutional encoder decoder for speech enhancement. International Journal of Advanced Science and Technology, 29(05), 772–777. http://sersc.org/journals/index.php/IJAST/article/view/9611
Karthik, A., & Mazher Iqbal, J. L. (2021). Efficient speech enhancement using recurrent convolution encoder and decoder. Wireless Personal Communication, 119, 1959–1973.
Kumawat, P., & Manikandan, M. S. (2019). SSQA: Speech signal quality assessment method using spectrogram and 2-D convolutional neural networks for improving efficiency of ASR devices. In 2019 Seventh international conference on digital information processing and communications (ICDIPC), 2019.
Lan, T., Lyu, Y., Ye, W., Hui, G., Xu, Z., & Liu, Q. (2020). Combining multi-perspective attention mechanism with convolutional networks for monaural speech enhancement. IEEE Access, 8, 78979–78991.
Li, A., Yuan, M., Zheng, C., & Li, X. (2020). Speech enhancement using progressive learning-based convolutional recurrent neural network. Applied Acoustics, 166, 107347.
Liu, C.-L., Fu, S.-W., Li, Y.-J., Huang, J.-W., Wang, H.-M., & Tsao, Y. (2020). Multichannel speech enhancement by raw waveform-mapping using fully convolutional networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing,. https://doi.org/10.1109/TASLP.2020.2976193
Llombart, J., González, D. R., Miguel, A., Vicente, L., Ortega, A., & Lleida, E. (2021). Progressive loss functions for speech enhancement with deep neural networks. EURASIP Journal on Audio, Speech, and Music Processing, 2021, 1–16.
Mashiana, H. S., Salaria, A., & Kaur, K. (2019). Speech enhancement using residual convolutional neural network. In 2019 International conference on smart systems and inventive technology (ICSSIT), 2019 (pp. 1193–1196).
Ouyang, Z., Yu, H., Zhu, W.-P., & Champagne, B. (2019). A fully convolutional neural network for complex spectrogram processing in speech enhancement. In ICASSP 2019—2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.
Pandey, A., & Wang, D. (2019a). TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain. In ICASSP 2019—2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.
Pandey, A., & Wang, D. (2019b). A new framework for CNN based speech enhancement in the time domain. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(7), 1179–1188.
Pandey, A., & Wang, D. (2020). Densely connected neural network with dilated convolutions for real-time speech enhancement in the time domain. In ICASSP 2020—2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020 (pp. 6629–6633).
Pandey, A., & Wang, D. (2021). Dense CNN with self-attention for time-domain speech enhancement. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1270–1279.
Parthasarathy, S., & Tashev, I. (2018). Convolutional neural network techniques for speech emotion recognition. In 2018 16th International workshop on acoustic signal enhancement (IWAENC), 2018.
Roy, S., & Paliwal, K. K. (2020). Causal convolutional neural network-based Kalman filter for speech enhancement. In 2020 IEEE Asia–Pacific conference on computer science and data engineering (CSDE), 2020 (pp. 1–6).
Roy, S. K., Nicolson, A., & Paliwal, K. K. (2021). DeepLPC-MHANet: Multi-head self-attention for augmented Kalman filter-based speech enhancement. IEEE Access, 9, 70516–70530.
Shah, N., Patil, H. A., & Soni, M. H. (2018). Time–frequency mask-based speech enhancement using convolutional generative adversarial network. In 2018 Asia–Pacific Signal and Information Processing Association annual summit and conference (APSIPA ASC), 2018.
Shi, Y., Rong, W., & Zheng, N. (2018). Speech enhancement using convolutional neural network with skip connections. In 2018 11th International symposium on Chinese spoken language processing (ISCSLP), 2018. https://doi.org/10.1109/iscslp.2018.8706591
Strake, M., Defraene, B., Fluyt, K., Tirry, W., & Fingscheidt, T. (2020). Fully convolutional recurrent networks for speech enhancement. In ICASSP 2020—2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020.
Tayseer, M., Adeel, A., & Hussain, A. (2018). A survey on techniques for enhancing speech. International Journal of Computer Applications, 179(17), 1–14.
Wu, B., Yu, M., Chen, L., Jin, M., Su, D., & Yu, D. (2019). Improving speech enhancement with phonetic embedding features. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU), 2019.
Author information
Authors and Affiliations
Contributions
There is no evidence of authorship.
Corresponding author
Ethics declarations
Conflict of interest
There is no potential for a conflict of interest with this project.
Salutation
No credit is due for this creation.
Ethical approval
This procedure is carried out without the involvement of people.
Rights of humans and animals
Animal and human rights are not being violated in any way.
Backing
There is no money associated with this effort.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Karthik, A., Mazher Iqbal, J.L. An optimized convolutional neural network for speech enhancement. Int J Speech Technol 26, 1117–1129 (2023). https://doi.org/10.1007/s10772-023-10073-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10772-023-10073-6