Skip to main content
SpringerLink
Log in

A study on unsupervised monaural reverberant speech separation

  • Published:
International Journal of Speech Technology Aims and scope Submit manuscript

Abstract

Separating individual source signals is a challenging task in musical and multitalker source separation. This work studies unsupervised monaural (co-channel) speech separation (UCSS) in reverberant environment. UCSS is the problem of separating the individual speakers from multispeaker speech without using any training data and with minimum information regarding mixing condition and sources. In this paper, state-of-art UCSS algorithms based on auditory and statistical approaches are evaluated for reverberant speech mixtures and results are discussed. This work also proposes to use multiresolution cochleagram and Constant Q Transform (CQT) spectrogram feature with two-dimensional Non-negative matrix factorization. Results show that proposed algorithm with CQT spectrogram feature gave an improvement of 1.986 and 1.262 in terms of speech intelligibility and 0.296 db and 0.561 db in terms of signal to interference ratio compared to state-of-art statistical and auditory approach respectively at T60 of 0.610s.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  • Chen, J., Wang, Y., & Wang, D. (2014). A feature study for classification-based speech separation at very low signal-to-noise ratio. In IEEE International conference on acoustics, speech and signal processing ICASSP 2014, Florence, Italy, May 4–9 (pp. 7039–7043). https://doi.org/10.1109/ICASSP.2014.6854965.

  • Cherry, E. C. (1953). Some experiments on the recognition of speech, with one and with two ears. The Journal of the Acoustical Society of America, 25(5), 975–979. https://doi.org/10.1121/1.1907229.

    Article  Google Scholar 

  • Chien, J. T., & Hsieh, H. L. (2012). Convex divergence ica for blind source separation. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 302–313. https://doi.org/10.1109/TASL.2011.2161080.

    Article  Google Scholar 

  • Delfarah, M., & Wang, D. (2017). Features for masking-based monaural speech separation in reverberant conditions. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(5), 1085–1094.

    Article  Google Scholar 

  • Fevotte, C., Bertin, N., & Durrieu, J. (2009). Nonnegative matrix factorization with the itakura-saito divergence: With application to music analysis. Neural Computation, 21(3), 793–830. https://doi.org/10.1162/neco.2008.04-08-771.

    Article  MATH  Google Scholar 

  • Gao, B., Woo, W. L., & Dlay, S. S. (2011). Single-channel source separation using emd-subband variable regularized sparse features. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 961–976. https://doi.org/10.1109/TASL.2010.2072500.

    Article  Google Scholar 

  • Gao, B., Woo, W. L., & Dlay, S. S. (2013). Unsupervised single-channel separation of nonstationary signals using gammatone filterbank and itakura saito nonnegative matrix two-dimensional factorizations. IEEE Transactions on Circuits and Systems I: Regular Papers, 60(3), 662–675. https://doi.org/10.1109/TCSI.2012.2215735.

    Article  MathSciNet  Google Scholar 

  • Hadad, E., Heese, F., Vary, P., & Gannot, S. (2014). Multichannel audio database in various acoustic environments. In 2014 14th international workshop on acoustic signal enhancement (IWAENC), Juan-les-Pins, France (pp. 313–317). https://doi.org/10.1109/IWAENC.2014.6954309.

  • Huang, P., Kim, M., Hasegawa-Johnson, M., & Smaragdis, P. (2015). Joint optimization of masks and deep recurrent neural networks for monaural source separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23(12), 2136–2147. https://doi.org/10.1109/TASLP.2015.2468583.

    Article  Google Scholar 

  • Hu, K., & Wang, D. (2013). An unsupervised approach to cochannel speech separation. IEEE Transactions on Audio, Speech, and Language Processing, 21(1), 122–131. https://doi.org/10.1109/TASL.2012.2215591.

    Article  MathSciNet  Google Scholar 

  • Hyvarinen, A. (1999). Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks, 10(3), 626–634. https://doi.org/10.1109/72.761722.

    Article  Google Scholar 

  • Krishna, P. K. M., & Ramaswamy, K. (2017). Single channel speech separation based on empirical mode decomposition and hilbert transform. IET Signal Processing, 11(5), 579–586. https://doi.org/10.1049/iet-spr.2016.0450.

    Article  Google Scholar 

  • Li, P., Guan, Y., Xu, B., & Liu, W. (2006). Monaural speech separation based on computational auditory scene analysis and objective quality assessment of speech. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 2014–2023. https://doi.org/10.1109/TASL.2006.883258.

    Article  Google Scholar 

  • Li, W., Wang, L., Zhou, Y., Dines, J., Doss, M. M., Bourlard, H., et al. (2014). Feature mapping of multiple beamformed sources for robust overlapping speech recognition using a microphone array. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 22(12), 2244–2255.

    Article  Google Scholar 

  • Madhu, N., & Martin, R. (2011). A versatile framework for speaker separation using a model-based speaker localization approach. IEEE Transactions on Audio, Speech and Language Processing, 19(7), 1900–1912.

    Article  Google Scholar 

  • Mesgarani, N., & Chang, E. F. (2012). Selective cortical representation of attended speaker in multi-talker speech perception. Nature, 485(5), 233–236.

    Article  Google Scholar 

  • Molla, M. K. I., & Hirose, K. (2007). Single-mixture audio source separation by subspace decomposition of hilbert spectrum. IEEE Transactions on Audio, Speech, and Language Processing, 15(3), 893–900. https://doi.org/10.1109/TASL.2006.885254.

    Article  Google Scholar 

  • Morgan, D. P., George, E. B., Lee, L. T., & Kay, S. M. (1995). Co-channel speaker separation. In 1995 international conference on acoustics, speech, and signal processing, Detroit, Michigan (Vol. 1, pp. 828–831). https://doi.org/10.1109/ICASSP.1995.479822.

  • Prasanna Kumar, M. K., & Kumaraswamy, R. (2017). Single-channel speech separation using empirical mode decomposition and multi pitch information with estimation of number of speakers. International Journal of Speech Technology, 20(1), 109–125. https://doi.org/10.1007/s10772-016-9392-y.

    Article  Google Scholar 

  • Rennie, S. J., Hershey, J. R., & Olsen, P. A. (2010). Single-channel multitalker speech recognition. IEEE Signal Processing Magazine, 27(6), 66–80.

    Google Scholar 

  • Saruwatari, H., Kawamura, T., Nishikawa, T., Lee, A., & Shikano, K. (2006). Blind source separation based on a fast-convergence algorithm combining ICA and beamforming. IEEE Transactions on Audio, Speech, and Language Processing, 14(2), 666–678. https://doi.org/10.1109/TSA.2005.855832.

    Article  Google Scholar 

  • Schmidt, M. N., & Olsson, R. K. (2006). Single-channel speech separation using sparse non-negative matrix factorization. In ISCA international conference on spoken language proceesing, INTERSPEECH, Pittsburgh, Pennsylvania.

  • Shao, Y., & Wang, D. (2003). Co-channel speaker identification using usable speech extraction based on multi-pitch tracking. In ıtIEEE international conference on acoustics, speech, and signal processing, Hong Kong, China (Vol. 2, pp. II–205–8). https://doi.org/10.1109/ICASSP.2003.1202330.

  • Smaragdis, P. (2007). Convolutive speech bases and their application to supervised speech separation. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 1–12. https://doi.org/10.1109/TASL.2006.876726.

    Article  Google Scholar 

  • Smaragdis, P. (2009). Relative-pitch tracking of multiple arbitary sounds. The Journal of the Acoustical Society of America, 125(5), 3406–3413.

    Article  Google Scholar 

  • Swamy, R. K., Murty, K. S. R., & Yegnanarayana, B. (2007). Determining number of speakers from multispeaker speech signals using excitation source information. IEEE Signal Processing Letters, 14(7), 481–484. https://doi.org/10.1109/LSP.2006.891333.

    Article  Google Scholar 

  • Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2010). A short-time objective intelligibility measure for time-frequency weighted noisy speech. In IEEE international conference on acoustics, speech and signal processing, Dallas, Texas, USA (pp. 4214–4217). https://doi.org/10.1109/ICASSP.2010.5495701.

  • Wang, D., & Chen, J. (2018). Supervised speech separation based on deep learning: An overview. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(10), 1702–1726. https://doi.org/10.1109/TASLP.2018.2842159.

    Article  MathSciNet  Google Scholar 

  • Wang, Y., & Wang, D. (2013). Towards scaling up classification-based speech separation. IEEE Transactions on Audio, Speech, and Language Processing, 21(7), 1381–1390. https://doi.org/10.1109/TASL.2013.2250961.

    Article  Google Scholar 

  • Wang, Z., & Wang, D. (2019). Combining spectral and spatial features for deep learning based blind speaker separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(2), 457–468.

    Article  Google Scholar 

  • Yegnanarayana, B., Swamy, R. K., & Prasanna, S. R. M. (2005). Separation of multispeaker speech using excitation information. NOLISP-2005, Barcelona, Spain (pp. 11–18).

  • Yegnanarayana, B., Swamy, R. K., & Murty, K. S. R. (2009). Determining mixing parameters from multispeaker data using speech-specific information. IEEE Transactions on Audio, Speech, and Language Processing, 17(6), 1196–1207. https://doi.org/10.1109/TASL.2009.2016230.

    Article  Google Scholar 

  • Zhang, X., & Wang, D. (2016). A deep ensemble learning method for monaural speech separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 24(5), 967–977. https://doi.org/10.1109/TASLP.2016.2536478.

    Article  MathSciNet  Google Scholar 

Download references

Funding

Funding was provided by Department of science and Technology, Government of India (Grant No. SR/WOS-A/ET-69/2016).

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Siddaganga Institute of Technology (Affiliated to Visvesvaraya Technological University, Belagavi), Tumakuru, 572103, India

    R. Hemavathi & R. Kumaraswamy

Authors
  1. R. Hemavathi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. R. Kumaraswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to R. Hemavathi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hemavathi, R., Kumaraswamy, R. A study on unsupervised monaural reverberant speech separation. Int J Speech Technol 23, 451–457 (2020). https://doi.org/10.1007/s10772-020-09706-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10772-020-09706-x

Keywords

Search

Navigation