Abstract
As an endangered language, Tujia language only rely on oral communication. There must exist noises in the process of collecting Tujia language corpus. This paper studies an end-to-end speech enhancement model based on improved deep convolutional generative adversarial network (DCGAN) to extract nearly pure Tujia language speech in noisy environment. Due to the low resource nature of Tujia language, using Chinese corpus as an extension of the Tujia language can effectively solve the problem of insufficient data. The speech enhancement function of the Tujia language was realized using the end-to-end method that consists of symmetric encoding and decoding. By modifying the loss function and network hierarchy parameters, adding the spectrum normalization and imbalanced learning rate made the model more stable during the training process. The experimental results show that the speech enhancement method proposed in this paper can achieve better noise reduction effect on the Tujia language dataset than traditional speech enhancement algorithm and neural network enhancement algorithms.
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
References
Shixuan, X.: On the recording and preservation of endangered language data. J. Guangxi Univ. Natl. (Philos. Soc. Sci. Ed.) 28(5), 11–15 (2006)
Hang, H.: Modern Speech Signal Processing, pp. 351–352. Electronic Industry Press, Beijing (2014)
Dailong, X., Guanyu, L., Ning, M.: Speech enhancement research based on spectral subtraction. J. Northwest University (Nat. Sci.) 38(02), 21–25, 87 (2017)
Navneet, U., Rahul, K.: Single channel speech enhancement: using wiener filtering with recursive noise estimation. Procedia Comput. Sci. 84, 22–30 (2016)
Chengli, S., Jianxiao, X., Yan, L.: A signal subspace speech enhancement approach based on joint low-rank and sparse matrix decomposition. Arch. Acoust. 41(2), 245–254 (2016)
Tamura, S., Waibel, A.: Noise reduction using connectionist models. ICASSP 1988(1), 553–556 (1988)
Yong, X., Jun, D., Lirong, D., et al.: An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 21(1), 65–68 (2014)
Shi, W., Zhang, X., Sun, M., et al.: Deep neural network based monaural speech enhancement with sparse and low-rank decomposition. In: IEEE 17th International Conference on Communication Technology (ICCT), pp. 1644–1647 (2017)
Huang, Q., Bao, C., Wang, X., et al.: DNN-based speech enhancement using MBE model. In: IWAENC, pp. 196–200 (2018)
Goodfellow, I., Pouget-Abadie, M., Mirza, B., et al.: Generative adversarial nets. In Advances in Neural Information Processing Systems (NIPS), pp. 2672–2680 (2014)
He, H., Philip S, Y., Changhu, W.: An introduction to image synthesis with generative adversarial nets. arXiv:1803.04469 (2018)
Jiaxian, G., Sidi, L., Han, C., et al.: Long text generation via adversarial training with leaked information. arXiv:1709.08624 (2017)
Engel, J., Agrawal, K.K., Chen, S., et al.: GANSynth: adversarial neural audio synthesis. In: ICLR (2019)
Pascual, S., Bonafonte, A., Serra, J.: SEGAN: speech enhancement generative adversarial network. In: INTERSPEECH (2017)
Alec, R., Luke, M.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)
Xiaojiao, M., Chunhua, S., Yubin, Y.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. arXiv:1603.09056 (2016)
Takeru, M., Toshiki, K., Masanori, K., et al.: Spectral normalization for generative adversarial networks. In: ICLR (2018)
Zhang, H., Goodfellow, I., Metaxas, D., et al.: Self-attention generative adversarial networks. arXiv:1805.08318 (2018)
Heusel, M., Ramsauer, H., Unterthiner, T., et al.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. arXiv:1706.08500 (2018)
Dong, W., Xuewei, Z.: THCHS-30: a free Chinese speech corpus. Comput. Sci. (2015)
Acknowledgment
This research is supported by Ministry of Education Humanities and Social Sciences Research Planning Fund Project, grant number 16YJAZH072, and Major projects of the National Social Science Fund, grant number 14ZDB156.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, C., Kang, M., Chen, Y., Li, M., Dai, T. (2019). Endangered Tujia Language Speech Enhancement Research Based on Improved DCGAN. In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics. CCL 2019. Lecture Notes in Computer Science(), vol 11856. Springer, Cham. https://doi.org/10.1007/978-3-030-32381-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-32381-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32380-6
Online ISBN: 978-3-030-32381-3
eBook Packages: Computer ScienceComputer Science (R0)