PEVD Parameters Demo

The clean speech signal is taken from the TIMIT corpus [1] while the room impulse responses are taken from the 3-channel mobile phone recordings from the ACE corpus [2]. In the examples, the anechoic speech signal is convolved with the room impulse responses before adding additive white Gaussian noise at the required SNR at each microphone.

The parameters of the PEVD-based speech enhancement algorithm which uses the Sequential Matrix Diagonalisation algorithm [3] are varied and investigated here.

Audio Examples

The audio player is built using the trackswitch.js tool in [7].

Speech enhancement for speech in -5 dB white noise in Lecture Room 2, T60 = 1.22 s

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s

Speech enhancement for speech in 5 dB white noise in Lecture Room 2, T65 = 1.22 s

Speech enhancement for speech in 20 dB white noise in Lecture Room 2, T620 = 1.22 s

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in -5 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 0 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 5 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

Speech enhancement for speech in 20 dB white noise in Lecture Room 2, T60 = 1.22 s, Fs = 16 kHz

References

[1] J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallet, N. L. Dahlgren, and V. Zue, "TIMIT acoustic-phonetic continuous speech corpus," Linguistic Data Consortium (LDC), Philadelphia, Corpus, 1993.

[2] J. Eaton, N. D. Gaubitch, A. H. Moore, and P. A. Naylor, “Estimation of room acoustic parameters: The ACE challenge,” IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 24, no. 10, pp. 1681-1693, Oct. 2016.

[3] S. Redif, S. Weiss, and J. G. McWhirter, “Sequential matrix diagonalisation algorithms for polynomial EVD of para-Hermitian matrices,” IEEE Trans. Signal Process., vol. 63, no. 1, pp. 81–89, Jan. 2015.

 

Related Works on PEVD Algorithms

[4] J. G. McWhirter, P. D. Baxter, T. Cooper, S. Redif, and J. Foster, “An EVD algorithm for para-Hermitian polynomial matrices,” IEEE Trans. Signal Process., vol. 55, no. 5, pp. 2158–2169, May 2007.

[5] V. W. Neo and P. A. Naylor, “Second order sequential best rotation algorithm with Householder transformation for polynomial matrix eigenvalue decomposition,” in Proc. IEEE Int. Conf. on Acoust., Speech and Signal Process. (ICASSP), 2019.

[6] S. Redif, S. Weiss, and J. G. McWhirter, “An approximate polynomial matrix eigenvalue decomposition algorithm for para-Hermitian matrices,” in Proc. Intl. Symp. on Signal Process. and Inform. Technology (ISSPIT), 2011, pp. 421–425.

 

Listening examples audio tool

[7] N. Werner, S. Balke, F.-R. Stöter, M. Müller, B. Edler, "trackswitch.js: A Versatile Web-Based Audio Player for Presenting Scientific Results." 3rd web audio conference, London, UK. 2017. [Online]. Available: https://github.com/audiolabs/trackswitch.js