Abstract
In this paper, we propose a speech recognition method based on CLSTM-HMM hybrid acoustic model for home service robots that cannot recognize speech commands effectively in domestic noise. Hybrid speech features characterize dynamic and static features, which can characterize speech features well, CNN has advantages in selecting good features, LSTM and HMM are usually used for speech recognition, which both methods have demonstrated strong capabilities. The experimental results prove that the recognition rate of home service robots based on CLSTM-HMM speech recognition method can reach 91.44%, 91.36% and 90.92%, respectively. Over all, the home service robots based on CLSTM-HMM speech recognition method have ideal recognition performance in domestic noise.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chivarov, N., Chikurtev, D., Pleva, M., Ondas, S.: Exploring human-robot interfaces for service mobile robots. In: 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA), Kosice, pp. 337–342 (2018)
Liu, C.-Y., Hung, T.-H., Cheng, K.-C., Li, T.-H.S.: HMM and BPNN based speech recognition system for home service robot. In: 2013 International Conference on Advanced Robotics and Intelligent Systems (2013)
Kumar, A., Rout, S.S., Goel, V.: Speech mel frequency cepstral coefficient feature classification using multi level support vector machine. In: Proceedings of the 2017 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics, pp. 134–138. IEEE, Piscataway (2017)
Shahin, I.: Emotion recognition based on third-order circular suprasegmental hidden Markov model. In: Proceedings of the 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, pp. 800–805. IEEE, Poscataway (2019)
Tazi, E.B.: A robust speaker identification system based on the combination of GFCC and MFCC methods. In: Prcoceedings of the 2017 International Conference on Multimedia Computing and Systems, pp. 54–58. IEEE Computer Society, Washington (2017)
Can, G., Akabas Cetin, A.E.: Recognition of acoustic signatures using non-linear teager energy based features. In: Proceedings of the 2016 International Workshop on Computational Intelligence for Multimedia Understanding, p. 78011900. IEEE, Piscataway (2016)
Van Hai, D., Chen, N.F., Lim, B.P.: Multi-task learning for phone recognition of under-resourced languages using mismatched transcription. IEEE/ACM Trans. Audio Speech Lang. Process. PP(99), 1 (2017)
Novoa, J., Wuth, J., Escudero, J.P., Fredes, J., Mahu, R., Yoma, N.B.: DNN-HMM Based Automatic Speech Recognition for HRI Scenarios (2018). 9781450349536
Liu, Y.: Research on continuous speech recognition with large vocabulary based on deep learning. Chongqing University of Posts and Telecommunications (2018)
Ying, T.: Research on acoustic event detection method based on CRNN-HMM. Shenyang University of Technology (2019)
Bukhari, D., Wang, Y., Wang, H.: Multilingual convolutional, long short-term memory, deep neural networks for low resource speech recognition. Procedia Comput. Sci. 107, 842–847 (2017)
Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764–1772 (2014)
Billa, J.: Dropout approaches for LSTM based speech recognition systems. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, pp. 5879–5883 (2018)
Zhang, H., Huang, H., Han, H.: Attention-based convolution skip bidirectional long short-term memory network for speech emotion recognition. IEEE Access 9, 5332–5342 (2021). https://doi.org/10.1109/ACCESS.2020.3047395
Zoughi, T., Homayounpour, M.M., Deypir, M.: Adaptive windows multiple deep residual networks for speech recognition. Expert Syst. Appl. 139, 112840 (2020), ISSN 0957-4174
Xiaohua, W., Pengchao, Y., Liping, M., Wenjie, W., Lei, Z.: Feature extraction algorithm for robot speech control in workshop environment. J. Xi’an Univ. Electron. Sci. Technol. 47(02), 16–22 (2020)
Lian, H.L., Zhou, J., Hu, Y.T., Zheng, W.M.: Conversion of whispered speech to normal speech using deep convolutional neural networks. J. Acoustics 45(01), 137–144 (2020)
Zhang, Q.Q., Liu, Y., Pan, J.L., et al.: Continuous speech recognition based on convolutional neural networks. J. Eng. Sci. 37(09), 1212–1217 (2015)
Peng, Y.L., Li, R., Ma, X.H., Li, Y.B.: Harmonic detection algorithm by Hanning dual-window full-phase FFT tri-spectral line interpolation. Power Sci. Eng. 37(04), 25–29 (2021)
Li, X.: Research on speech feature parameter extraction method. Xi'an University of Electronic Science and Technology (2006)
Bai, J., Shi, Y.Y., Xue, P.Y., et al.: Fusion of nonlinear power function and spectral subtraction method for CFCC feature extraction. J. Xi’an Univ. Electron. Sci. Technol. 46(1), 86–92 (2019)
Bandela, S.R., Kumar, T.K.: Stressed speech emotion recognition using feature fusion of teager energy operator and MFCC. In: Proceedings of the 2017 8th International Conference on Computing, Communications and Networking Technologies, Piscataway, p. 8204149. IEEE (2017)
Monteiro, R.L.D.C., Pererra, V., Costa, H.G.: Analusis of the better life index trough a cluster algorithm. Soc. Indicators Res. 142(2), 477–506 (2019)
Liu, J.H.: Chinese Speech Recognition based on Deep Convolutional Neural Network. Taiyuan University of Technology, Taiyuan (2019)
Fan, Y.Y.: A Deep Learning Approach for Speaker Recognition . Nanchang University of Aviation, Nanchang (2019)
Huang, R.: Experimental design of Chinese speech recognition based on Bi-RNN. Modern Comput. (Professional Edition) 10, 92–95 (2019)
Sun, L., Du, J., Dai, L.R., et al.: Multiple-target deep learning for LSTM-RNN based speech enhancement. In: 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA). IEEE (2017)
Zhang, Z.T.: Research on speech recognition technology based on wavelet and PNCC feature parameters. Chongqing University (2018)
Feng, Y.: Speech recognition technology based on the study of HMM and DNN hybrid model. Hebei University of Science and Technology (2020)
Acknowledgements
This work was supported by Natural Science Foundation of China [51905405]; Key research & Development plan of Shaanxi province China [2019ZDLGY01-08]; Ministr of Education Engineering Science and Technology Talent Training Research Project of China [18JDGC029].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, C., Wang, X., Zhang, L. (2021). Speech Recognition Method for Home Service Robots Based on CLSTM-HMM Hybrid Acoustic Model. In: Huang, DS., Jo, KH., Li, J., Gribova, V., Bevilacqua, V. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science(), vol 12836. Springer, Cham. https://doi.org/10.1007/978-3-030-84522-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-84522-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84521-6
Online ISBN: 978-3-030-84522-3
eBook Packages: Computer ScienceComputer Science (R0)