MATLAB software

• COLEA: A software tool for speech analysis

• PESQ and other objective measures for evaluating quality of speech processed by noise suppression algorithms [composite.zip]

              Relevant references:

  • Quality Assessment:   Hu, Y. and Loizou, P. (2008). “Evaluation of objective quality measures for speech enhancement,” IEEE Transactions on Speech and Audio Processing, 16(1), 229-238. 

  • Intelligibility Assessment:  Ma, J., Hu, Y. and Loizou, P. (2009). "Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions", Journal of the Acoustical Society of America, 125(5), 3387-3405.

• Speech Enhancement Code
  •  Lu, Y. and Loizou, P. (2008).  "A geometric approach to spectral subtraction," Speech Communication, 50, 453-466, 2008 - MATLAB code: [GA_code.zip]

  • Lu, Y. and Loizou, P. (2011). "Estimators of The Magnitude-Squared Spectrum and Methods for Incorporating SNR Uncertainty," IEEE Trans. Audio, Speech, Language Processing,19(5), 1123-1137.[MATLAB code] [pdf].

  • [AMS_features.rar]   -  Kim, G., Lu, Y., Hu, Y. and Loizou, P. (2009). "An algorithm that improves speech intelligibility in noise for normal-hearing listeners," Journal of Acoustical Society of America, 126(3), 1486-1494. [pdf] [Audio Demos]

   

• Ideal binary mask and other ideal channel selection algorithms  [ICS.zip] - (for more information see: readme)

  Li, N. and Loizou, P. (2008). “Factors influencing intelligibility of ideal binary-masked speech: Implications for noise reduction,” Journal of Acoustical Society of America, 123(3), 1673–1682. [pdf]

  Loizou, P.  and Kim, G. (2011). "Reasons why Current Speech-Enhancement Algorithms do not Improve Speech Intelligibility and Suggested Solutions," IEEE Trans. Audio, Speech, Language Processing, 19(1), 47-56. [pdf]

• Objective measures for predicting speech intelligibility
  • Loizou, P. and Ma, J. (2011). "Extending the articulation index to  account for non-linear distortions introduced by noise-suppression algorithms," J. Acoust. Soc. Am., 130(2), 986-995. [pdf] [MATLAB code]
•  Ma, J. and Loizou, P.C. (2011) "SNR Loss: A new objective measure for predicting the intelligibility of noise-suppressed speech," Speech Comm., 53, 340-354. MATLAB code: [SNRloss.rar]   

 

Home