Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Mask-Based Beamforming Applied to the End-Fire Microphone Array

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

Multi-channel speech enhancement techniques are mainly based on optimal multi-channel speech estimators that comprise a minimum variance distortionless response (MVDR) beamformer followed by a single-channel Wiener post-filter. There are two problems in the application of this theoretically optimal solution. The first is the high sensitivity of the MVDR beamformer to errors in the estimated acoustic transfer function (ATF). The second is the accuracy of the time-varying post-filter coefficients estimated from non-stationary speech and noise. Mask-based beamforming developed in the last decade considerably improves the performance of the MVDR beamformer. In addition, the estimated time–frequency mask can be successfully used in post-filter design. In this paper, we propose several improvements to this approach. First, we propose an end-fire microphone array with a better directivity index than the corresponding broadside array. The proposed microphone array is composed of unidirectional microphone capsules that increase the directivity of the microphone array. Second, we propose preprocessing using a delay-and-sum beamformer before estimating the ideal ratio mask (IRM). Next, we propose a simplified generalized sidelobe canceller (S-GSC), which does not need to estimate ATF. We also improved the design of its blocking matrix by scaling the null space eigenvectors of the speech covariance matrix. The proposed computationally efficient multiple iteration method improves the adaptation of the S-GSC parameters. Finally, we improved the previous IRM-based post-filter, considering the SNR improvement at the output of the S-GSC beamformer. The integral speech enhancement procedure was tested on real room recordings using PESK, STOI, and SDR measures.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data Availability

The datasets generated and analyzed during the current study are available from the corresponding author upon reasonable request.

Notes

  1. To be more precise, the principal eigenvector is equal to AT up to a multiplicative complex constant.

References

  1. J. Barker, R. Marxer, E. Vincent, S. Watanabe, The third ‘CHiME’ speech separation and recognition challenge: analysis and outcomes. Comput. Speech Lang. 46, 605–626 (2017). https://doi.org/10.1016/J.CSL.2016.10.005

    Article  Google Scholar 

  2. J. Benesty, J. Chen, Y. Huang, Microphone array signal processing, in Springer Topics in Signal Processing (Springer, 2008), pp. 1–240. https://doi.org/10.1007/978-3-540-78612-2

  3. B.R. Breed, J. Strauss, A short proof of the equivalence of LCMV and GSC beamforming. IEEE Signal Process. Lett. 9, 168–169 (2002). https://doi.org/10.1109/LSP.2002.800506

    Article  ADS  Google Scholar 

  4. K.M. Buckley, L.J. Griffiths, Adaptive generalized sidelobe canceller with derivative constraints. IEEE Trans. Antennas Propag. AP-34, 311–319 (1986). https://doi.org/10.1109/tap.1986.1143832

    Article  ADS  Google Scholar 

  5. J. Capon, High-resolution frequency-wavenumber spectrum analysis. Proc. IEEE 57, 1408–1418 (1969). https://doi.org/10.1109/PROC.1969.7278

    Article  Google Scholar 

  6. J. Chen, Y. Wang, D. Wang, A feature study for classification-based speech separation at low signal-to-noise ratios. IEEE/ACM Trans. Audio Speech Lang. Process. 22, 1993–2002 (2014). https://doi.org/10.1109/TASLP.2014.2359159

    Article  Google Scholar 

  7. F. Chollet, Deep Learning with Python (Manning Publications, 2017)

  8. J. Du, Y.H. Tu, L. Sun, F. Ma, H.K. Wang, J. Pan, C. Liu, J.D. Chen, C.H. Lee, The USTC-iFlytek system for CHiME-4 challenge. Proc. CHiME 4, 36–38 (2016)

    Google Scholar 

  9. G.W.X. Elko, Differential microphone arrays, in Audio Signal Processing for Next-Generation Multimedia Communication Systems. ed. by Y. Huang, J. Benesty (Springer, Boston, 2004). https://doi.org/10.1007/1-4020-7769-6_2

    Chapter  Google Scholar 

  10. K. Eneman, M. Moonen, Iterated partitioned block frequency-domain adaptive filtering for acoustic echo cancellation. IEEE Trans. Speech Audio Process. 11(2), 143–158 (2003)

    Article  Google Scholar 

  11. H. Erdogan, T. Hayashi, J. R. Hershey, T. Hori, C. Hori, W. N. Hsu, S. Kim, J. L. Roux, Z. Meng, S. Watanabe, Multi-channel speech recognition: LSTMs all the way through, in CHiME-4 Workshop (2016), pp. 1–4

  12. H. Erdogan, J. R. Hershey, S. Watanabe, J. Le Roux, Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks, in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2015), pp. 708–712. https://doi.org/10.1109/ICASSP.2015.7178061

  13. H. Erdogan, J. R. Hershey, S. Watanabe, M. I. Mandel, J. Le Roux, Improved mvdr beamforming using single-channel mask prediction networks, in Interspeech (2016), pp. 1981–1985

  14. J.M. Festen, R. Plomp, Effects of fluctuating noise and interfering speech on the speech-reception threshold for impaired and normal hearing. J. Acoust. Soc. Am. 88(4), 1725–1736 (1990)

    Article  ADS  PubMed  CAS  Google Scholar 

  15. O.L. Frost, An algorithm for linearly constrained adaptive array processing. Proc. IEEE 60, 926–935 (1972). https://doi.org/10.1109/PROC.1972.8817

    Article  Google Scholar 

  16. S. Gannot, D. Burshtein, E. Weinstein, Signal enhancement using beamforming and nonstationarity with applications to speech. IEEE Trans. Signal Process. 49, 1614–1626 (2001). https://doi.org/10.1109/78.934132

    Article  ADS  Google Scholar 

  17. S. Gannot, E. Vincent, S. Markovich-Golan, A. Ozerov, A Consolidated perspective on multimicrophone speech enhancement and source separation. IEEE/ACM Trans. Audio Speech Lang. Process. 25, 692–730 (2017). https://doi.org/10.1109/TASLP.2016.2647702

    Article  Google Scholar 

  18. J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, N.L. Dahlgren, V. Zue, TIMIT Acoustic-Phonetic Continuous Speech Corpus—Linguistic Data Consortium (No. LDC93S1), (University of Pennsylvania, 1993). https://doi.org/10.35111/17gk-bn40

  19. L.J. Griffiths, C.W. Jim, An alternative approach to linearly constrained adaptive beamforming. IEEE Trans. Antennas Propag. 30, 27–34 (1982). https://doi.org/10.1109/TAP.1982.1142739

    Article  ADS  Google Scholar 

  20. R. Haeb-Umbach, J. Heymann, L. Drude, S. Watanabe, M. Delcroix, T. Nakatani, Far-field automatic speech recognition. Proc. IEEE 109, 124–148 (2020). https://doi.org/10.1109/JPROC.2020.3018668

    Article  Google Scholar 

  21. J.W. Hall, E. Buss, J.H. Grose, P.A. Roush, Effects of age and hearing impairment on the ability to benefit from temporal and spectral modulation. Ear Hear. 33(3), 340 (2012)

    Article  PubMed  PubMed Central  Google Scholar 

  22. J. Heymann, M. Bacchiani, T.N. Sainath, Performance of mask based statistical beamforming in a smart home scenario, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2018), pp. 6722–6726. https://doi.org/10.1109/ICASSP.2018.8462372

  23. J. Heymann, L. Drude, R. Haeb-Umbach, Neural network based spectral mask estimation for acoustic beamforming, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings (Institute of Electrical and Electronics Engineers Inc. 2016), pp. 196–200. https://doi.org/10.1109/ICASSP.2016.7471664

  24. J. Heymann, L. Drude, R. Haeb-Umbach, Wide residual BLSTM network with discriminative speaker adaptation for robust speech recognition, in CHiME 2016 workshop, vol. 78, p. 79 (2016)

  25. C. Marro, Y. Mahieux, K.U. Simmer, Analysis of noise reduction and dereverberation techniques based on microphone arrays with postfiltering. IEEE Trans. Speech Audio Process. 6, 240–259 (1998). https://doi.org/10.1109/89.668818

    Article  Google Scholar 

  26. I.A. McCovan, H. Bourlard, Microphone array post-filter based on noise field coherence. IEEE Trans. Speech Audio Process. 11, 709–716 (2003). https://doi.org/10.1109/TSA.2003.818212

    Article  Google Scholar 

  27. T. Menne, J. Heymann, A. Alexandridis, K. Irie, A. Zeyer, P. Golik, I. Kulikov, L. Drude, R. Schlüter, H. Ney, R. Häb-Umbach, A. Mouchtaris, The RWTH/UPB/FORTH system combination for the 4th CHiME challenge evaluation, in 4th CHiME Speech Separation and Recognition Challenge Workshop (2016)

  28. C. Pan, J. Chen, J. Benesty, On the noise reduction performance of the MVDR beamformer in noisy and reverberant environments, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings (IEEE, 2014), pp. 815–819. https://doi.org/10.1109/ICASSP.2014.6853710

  29. L. Pfeifenberger, M. Zohrer, F. Pernkopf, DNN-based speech mask estimation for eigenvector beamforming, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings (Institute of Electrical and Electronics Engineers Inc., 2017), pp. 66–70. https://doi.org/10.1109/ICASSP.2017.7952119

  30. A.W. Rix, J.G. Beerends, M.P. Hollier, A.P. Hekstra, Perceptual evaluation of speech quality (PESQ)—a new method for speech quality assessment of telephone networks and codecs, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings, pp. 749–752 (2001). https://doi.org/10.1109/icassp.2001.941023

  31. Z.M. Šarić, I.I. Papp, D.D. Kukolj, I. Velikić, G. Velikić, Partitioned block frequency domain acoustic echo canceller with fast multiple iterations. Digital Signal Process. 27, 119–128 (2014)

    Article  Google Scholar 

  32. Z.M. Saric, D.P. Simic, S.T. Jovicic, A new post-filter algorithm combined with two-step adaptive beamformer. Circuits Syst. Signal Process. 30, 483–500 (2011). https://doi.org/10.1007/s00034-010-9233-1

    Article  Google Scholar 

  33. Z.M. Šarić, M. Subotić, R. Bilibajkić, M. Barjaktarović, J. Stojanović, Supervised speech separation combined with adaptive beamforming. Comput. Speech Lang. 76, 101409 (2022). https://doi.org/10.1016/j.csl.2022.101409

    Article  Google Scholar 

  34. Z.M. Saric, M. Subotic, R. Bilibajkic, M. Barjaktarovic, N. Zdravkovic, Performance analysis of MVDR beamformer applied on an end-fire microphone array composed of unidirectional microphones. Arch. Acoust. 46(4), 611–621 (2021). https://doi.org/10.24425/aoa.2021.138154

    Article  Google Scholar 

  35. S. Siami-Namini, N. Tavakoli, A.S. Namin, The performance of LSTM and BiLSTM in forecasting time series, in IEEE International Conference on Big Data (Big Data) (2019), pp. 3285–3292. https://doi.org/10.1109/BigData47090.2019.9005997

  36. K.U. Simmer, J. Bitzer, C. Marro, Post-filtering techniques, in Microphone Arrays. ed. by M. Brandstein, D. Ward (Springer, Berlin, 2001), pp. 39–60. https://doi.org/10.1007/978-3-662-04619-7_3

    Chapter  Google Scholar 

  37. M. Souden, J. Benesty, S. Affes, On optimal frequency-domain multichannel linear filtering for noise reduction. IEEE Trans. Audio Speech Lang. Process. 18(2), 260–276 (2009)

    Article  Google Scholar 

  38. M. Strake, B. Defraene, K. Fluyt, W. Tirry, T. Fingscheidt, Speech enhancement by LSTM-based noise suppression followed by CNN-based speech restoration. EURASIP J. Adv. Signal Process. 2020, 49 (2020). https://doi.org/10.1186/s13634-020-00707-1

    Article  ADS  Google Scholar 

  39. C.H. Taal, R.C. Hendriks, R. Heusdens, J. Jensen, An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19, 2125–2136 (2011). https://doi.org/10.1109/TASL.2011.2114881

    Article  Google Scholar 

  40. Y. Tachioka, S. Watanabe, T. Hori, The MELCO/MERL system combination approach for the fourth CHiME challenge, in Proceedings of the Fourth CHiME Challenge Workshop (2016), pp. 1–3

  41. H.L. Van Trees, Optimum Array Processing (Wiley, New York, 2002). https://doi.org/10.1002/0471221104

    Book  Google Scholar 

  42. A. Varga, H.J.M. Steeneken, Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12, 247–251 (1993). https://doi.org/10.1016/0167-6393(93)90095-3

    Article  Google Scholar 

  43. E. Vincent, R. Gribonval, C. Févotte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14, 1462–1469 (2006). https://doi.org/10.1109/TSA.2005.858005

    Article  Google Scholar 

  44. D. Wang, J. Chen, Supervised speech separation based on deep learning: an overview. IEEE/ACM Trans. Audio Speech Lang. Process. (2018). https://doi.org/10.1109/TASLP.2018.2842159

    Article  PubMed  PubMed Central  Google Scholar 

  45. Y. Wang, K. Han, D. Wang, Exploring monaural features for classification-based speech segregation. IEEE Trans. Audio Speech Lang. Process. Trans. Audio Speech Lang. Process. 21(2), 270–279 (2013)

    Article  Google Scholar 

  46. Y. Wang, A. Narayanan, D.L. Wang, On training targets for supervised speech separation. IEEE/ACM Trans. Audio Speech Lang. Process. 22, 1849–1858 (2014). https://doi.org/10.1109/TASLP.2014.2352935

    Article  PubMed  PubMed Central  Google Scholar 

  47. E. Warsitz, R. Haeb-Umbach, Blind acoustic beamforming based on generalized eigenvalue decomposition. IEEE Trans. Audio Speech Lang. Process. 15(5), 1529–1539 (2007)

    Article  Google Scholar 

  48. F. Weninger, H. Erdogan, S. Watanabe, E. Vincent, J. Le Roux, J.R. Hershey, B. Schuller, Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR, in Latent variable analysis and signal separation. LVA/ICA 2015. Lecture Notes in Computer Science, vol. 9237, ed. by E. Vincent, A. Yeredor, Z. Koldovský, P. Tichavský (Springer, Cham, 2015). https://doi.org/10.1007/978-3-319-22482-4_11

    Chapter  Google Scholar 

  49. H. Xiang, B. Wang, Z. Ou, The THU-SPMI CHiME-4 system: lightweight design with advanced multi-channel processing, feature enhancement, and language modeling, in CHiME-4 Workshop (2016)

  50. X. Xiao, S. Zhao, D.H.H. Nguyen, X. Zhong, D.L. Jones, E.S. Chng, H. Li, The NTU-ADSC systems for reverberation challenge 2014, in Proceedings of REVERB Challenge Workshop (Spoken Language Systems MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA, 2014), p. 2

  51. T. Yoshioka, N. Ito, M. Delcroix, A. Ogawa, K. Kinoshita, M. Fujimoto, C. Yu, W.J. Fabian, M. Espi, T. Higuchi, S. Araki, T. Nakatani, The NTT CHiME-3 system: advances in speech enhancement and recognition for mobile multi-microphone devices, in 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015—Proceeding (2016), pp. 436–443. https://doi.org/10.1109/ASRU.2015.7404828

  52. R. Zelinski, A microphone array with adaptive post-filtering for noise reduction in reverberant rooms, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings (IEEE, 1988), pp. 2578–2581. https://doi.org/10.1109/icassp.1988.197172

  53. X. Zhang, Z.Q. Wang, D. Wang, A speech enhancement algorithm by iterating single- and multi-microphone processing and its application to robust ASR, in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings (Institute of Electrical and Electronics Engineers Inc., 2017), pp. 276–280. https://doi.org/10.1109/ICASSP.2017.7952161

  54. X.L. Zhang, Deep ad-hoc beamforming. Comput. Speech Lang. (2021). https://doi.org/10.1016/j.csl.2021.101201

    Article  Google Scholar 

Download references

Acknowledgements

This paper results from research funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia.

Author information

Authors and Affiliations

  1. Laboratory of Acoustics, Life Activities Advancement Institute, Gospodar Jovanova 35, 11000, Belgrade, Serbia

    Zoran Šarić, Miško Subotić & Ružica Bilibajkić

  2. Faculty of Electrical Engineering, University of Belgrade, Bulevar Kralja Aleksandra 73, 11120, Belgrade, Serbia

    Marko Barjaktarović

  3. Faculty of Medical Sciences, University of Kragujevac, Svetozara Markovića 69, 34000, Kragujevac, Serbia

    Jasmina Stojanović

Authors
  1. Zoran Šarić
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miško Subotić
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ružica Bilibajkić
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marko Barjaktarović
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jasmina Stojanović
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zoran Šarić.

Ethics declarations

Competing interest

The authors declare that there are no conflicts of interest regarding the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

The computational complexity of individual processing steps for the proposed solution is displayed in Tables 5, 6 and 7. Constants used in the calculations are defined in Table 4. Table 8 displays a summary.

Table 5 Computational complexity for DNN features calculation
Full size table
Table 6 Computational complexity for DNN-based masks prediction
Full size table
Table 7 Computational complexity for S-GSC, post-filter, and in/out FFTs
Full size table
Table 8 Summary of complexity analysis
Full size table

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Šarić, Z., Subotić, M., Bilibajkić, R. et al. Mask-Based Beamforming Applied to the End-Fire Microphone Array. Circuits Syst Signal Process 43, 1661–1696 (2024). https://doi.org/10.1007/s00034-023-02530-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-023-02530-z

Keywords

Search

Navigation