Relative Transfer Function Estimation from Speech Keywords

  • Ryan M. CoreyEmail author
  • Andrew C. Singer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10891)


Far-field speech capture systems rely on microphone arrays to spatially filter sound, attenuating unwanted interference and noise and enhancing a speech signal of interest. To design effective spatial filters, we must first estimate the acoustic transfer functions between the source and the microphones. It is difficult to estimate these transfer functions if the source signals are unknown. However, in systems that are activated by a particular speech phrase, we can use that phrase as a pilot signal to estimate the relative transfer functions. Here, we propose a method to estimate relative transfer functions from known speech phrases in the presence of background noise and interference using template matching and time-frequency masking. We find that the proposed method can outperform conventional estimation techniques, but its performance depends on the characteristics of the speech phrase.


Relative transfer function Multichannel source separation Keyword spotting Microphone array 


  1. 1.
    Gannot, S., Vincent, E., Markovich-Golan, S., Ozerov, A.: A consolidated perspective on multimicrophone speech enhancement and source separation. IEEE/ACM Trans. Audio Speech Lang. Process. 25(4), 692–730 (2017)CrossRefGoogle Scholar
  2. 2.
    Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F., Matassoni, M.: The second ‘CHiME’ speech separation and recognition challenge: datasets, tasks and baselines. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 126–130 (2013)Google Scholar
  3. 3.
    Doclo, S., Kellermann, W., Makino, S., Nordholm, S.E.: Multichannel signal enhancement algorithms for assisted listening devices. IEEE Sign. Process. Mag. 32(2), 18–30 (2015)CrossRefGoogle Scholar
  4. 4.
    Gannot, S., Burshtein, D., Weinstein, E.: Signal enhancement using beamforming and nonstationarity with applications to speech. IEEE Trans. Sign. Process. 49(8), 1614–1626 (2001)CrossRefGoogle Scholar
  5. 5.
    Cohen, I.: Relative transfer function identification using speech signals. IEEE Trans. Speech Audio Process. 12(5), 451–459 (2004)CrossRefGoogle Scholar
  6. 6.
    Markovich, S., Gannot, S., Cohen, I.: Multichannel eigenspace beamforming in a reverberant noisy environment with multiple interfering speech signals. IEEE Trans. Audio Speech Lang. Process. 17(6), 1071–1086 (2009)CrossRefGoogle Scholar
  7. 7.
    Makino, S., Lee, T.W., Sawada, H.: Blind Speech Separation. vol. 615. Springer, New York (2007)Google Scholar
  8. 8.
    Pedersen, M.S., Larsen, J., Kjems, U., Parra, L.C.: Convolutive blind source separation methods. In: Benesty, J., Sondhi, M.M., Huang, Y.A. (eds.) Springer Handbook of Speech Processing. SH, pp. 1065–1094. Springer, Heidelberg (2008). Scholar
  9. 9.
    Corey, R., Singer, A.: Real-world evaluation of multichannel audio enhancement using acoustic pilot signals. In: Asilomar Conference on Signals, Systens, and Computers. (2017)Google Scholar
  10. 10.
    Chen, G., Parada, C., Heigold, G.: Small-footprint keyword spotting using deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4087–4091 (2014)Google Scholar
  11. 11.
    Van Trees, H.: Optimum Array Processing. Wiley, New York (2004)Google Scholar
  12. 12.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoustics Speech Sign. Process. 26(1), 43–49 (1978)CrossRefGoogle Scholar
  13. 13.
    Yilmaz, O., Rickard, S.: Blind separation of speech mixtures via time-frequency masking. IEEE Trans. Sign. Process. 52(7), 1830–1847 (2004)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Araki, S., Okada, M., Higuchi, T., Ogawa, A., Nakatani, T.: Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 385–389 (2016)Google Scholar
  15. 15.
    Koldovskỳ, Z., Málek, J., Gannot, S.: Spatial source subtraction based on incomplete measurements of relative transfer function. IEEE Trans. Audio Speech Lang. Process. 23(8), 1335–1347 (2015)CrossRefGoogle Scholar
  16. 16.
    Warden, P.: Speech commands: a public dataset for single-word speech recognition (2017). Dataset available from
  17. 17.
    Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallett, D.: TIMIT acoustic-phonetic continuous speech corpus LDC93S1. Web Download (1993)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations