Abstract
In order to solve the problem of instability of the traditional speech separation algorithm, a kind of reverberation speech separation model based on deep learning is proposed. The problem of speech separation in reverberation environment has been studied. The auditory scene analysis is used to simulate the human auditory perception ability. According to the ideal two value mode principle, the target speech signal can be extracted. Moreover, the deep neural network (DNN) shows great learning ability in speech recognition and artificial intelligence. In this paper, a DNN model is proposed to learn the inverse reverberation and denoising by learning the spectrum mapping between “contaminated” speech and pure speech. By extracting a series of spectrum features, the time dynamic information of adjacent frames is fused. The DNN is used to transform the coded spectrum, and restore the pure voice frequency spectrum. Finally, the time domain signal is reconstructed. In addition, the feature classification ability of DNN is also proposed to complete the separation of double sound reverberation speech. The binaural features ITD and ILD and the mono features GFCC are fused to form a long eigenvector. The DNN is pre-trained by RBM to complete the classification task. The results show that the proposed model improves the quality and intelligibility of the speech separation, and enhances the stability of the system significantly.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Barker, J.P.: Evaluation of scene analysis using real and simulated acoustic mixtures: lessons learnt from the chime speech recognition challenges. J. Acoust. Soc. Am. 141(5), 3693–3693 (2017)
Asaei, A., Taghizadeh, M. J., Cevher, V.: Computational methods for underdetermined convolutive speech localization and separation via model-based sparse component analysis. Speech Commun. 76(C), 201–217 (2016)
Josupeit, A., Kopčo, N., Hohmann, V.: Modeling of speech localization in a multi-talker mixture using periodicity and energy-based auditory features. J. Acoust. Soc. Am. 139(5), 2911 (2016)
Scholes, C., Palmer, A.R., Sumner, C.J.: Stream segregation in the anesthetized auditory cortex. Hear. Res. 328(2), 48–58 (2015)
Denham, S., Coath, M.: The role of form in modeling auditory scene analysis. J. Acoust. Soc. Am. 137(4), 2249–2249 (2015)
Vander, G.M., Bourguignon, M., de Beeck, M., Wens, V., Marty, B., Hassid, S., et al.: Left superior temporal gyrus is coupled to attended speech in a cocktail-party auditory scene. J. Neurosci. 36(5), 1596–1606 (2016)
Rogalsky, C., Poppa, T., Chen, K.H., Anderson, S.W., Damasio, H., Love, T., et al.: Speech repetition as a window on the neurobiology of auditory-motor integration for speech: a voxel-based lesion symptom mapping study. Neuropsychologia 71(01), 18 (2015)
White-Schwoch, T., Davies, E.C., Thompson, E.C., Carr, K.W., Nicol, T., Bradlow, A.R., et al.: Auditory-neurophysiological responses to speech during early childhood: effects of background noise. Hear. Res. 328, 34–47 (2015)
Moossavi, A., Mehrkian, S., Lotfi, Y., Faghih Zadeh, S., Adjedi, H.: The effect of working memory training on auditory stream segregation in auditory processing disorders children. Optics Commun 281(9), 2491–2497 (2015)
Kenway, B., Tam, Y.C., Vanat, Z., Harris, F., Gray, R., Birchall, J., et al.: Pitch discrimination: an independent factor in cochlear implant performance outcomes. Otol. Neurotol. 36(9), 1472–1479 (2015)
Mathon, B., Ulvin, L.B., Adam, C., Baulac, M., Dupont, S., Navarro, V., et al.: Surgical treatment for mesial temporal lobe epilepsy associated with hippocampal sclerosis. Revue Neurol. 171(3), 315–325 (2015)
Leclère, T., Lavandier, M., Culling, J.F.: Speech intelligibility prediction in reverberation: towards an integrated model of speech transmission, spatial unmasking, and binaural de-reverberation. J. Acoust. Soc. Am. 137(6), 3335–3345 (2015)
Léger, A.C., Reed, C.M., Desloge, J.G., Swaminathan, J., Braida, L.D.: Consonant identification in noise using hilbert-transform temporal fine-structure speech and recovered-envelope speech for listeners with normal and impaired hearing. J. Acoust. Soc. Am. 138(1), 389–403 (2015)
Koralus, P.: Can visual cognitive neuroscience learn anything from the philosophy of language? ambiguity and the topology of neural network models of multistable perception. Synthese 193(5), 1409–1432 (2016)
Acknowledgement
The authors acknowledge the National Natural Science Foundation of China (Grant: 61372146, 61373098), the Youth Natural Science Foundation of Jiangsu Province of China (Grant: BK20160361), the Qinglan Project Young and Middle-aged Academic Leader Foundation of Jiangsu Province, the Professional Leader Advanced Research Project Foundation of Higher Vocational College of Jiangsu Province (Grant: 2017GRFX046).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhou, Y., Zhao, H., Chen, J. et al. Research on speech separation technology based on deep learning. Cluster Comput 22 (Suppl 4), 8887–8897 (2019). https://doi.org/10.1007/s10586-018-2013-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-018-2013-6