[AUDITORY] 8 speech intelligibility models available (LAVANDIER Mathieu )

Subject: [AUDITORY] 8 speech intelligibility models available From: LAVANDIER Mathieu <000002f7cc5c2340-dmarc-request@xxxxxxxx> Date: Fri, 11 Sep 2026 14:24:55 +0000 --_000_bd083ae02cc94456b84528253ad33803entpefr_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Dear list, We have developed several models allowing to predict speech intelligibility= in noise and reverberation. Most of them are using as inputs the signals a= t the listener's ears (some use binaural room impulse responses) to predict= differences in speech reception threshold between different conditions. Th= ere are different model versions that predict different effects: binaural h= earing (spatial release from masking), dip listening, the effect of hearing= loss (taking the listener's audiogram as additional input), multiple effec= ts of reverberation, and harmonic cancellation. You can find them here: https://mathieulavandier.wordpress.com/home/models/ With each model, there is an example of the predictions corresponding to on= e dataset from the literature. You have access to the signals used in the s= peech intelligibility test, along with the data resulting from this test (l= isteners' SRTs), and the code used to run the model on this dataset; so tha= t you can check how to handle a model before using it to predict intelligib= ility in other conditions. Do not hesitate to play around with these models and give us feedback! We h= ope they can be useful. All the best, mat ---------------------------------------------------------------------------= -------------------- Mathieu Lavandier https://mathieulavandier.wordpress.com/ Universit=E9 de Lyon, Labex CeLyA https://celya.universite-lyon.fr<https://celya.universite-lyon.fr/> ENTPE, Laboratoire de Tribologie et Dynamique des Syst=E8mes (LTDS, UMR 551= 3) Rue M. Audin, 69518 Vaulx-en-Velin Cedex, FRANCE T=E9l : +33 (0)4 72 04 70 30 --_000_bd083ae02cc94456b84528253ad33803entpefr_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable <html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr= osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" = xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:= //www.w3.org/TR/REC-html40"> <head> <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Diso-8859-= 1"> <meta name=3D"Generator" content=3D"Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang=3D"FR" link=3D"#0563C1" vlink=3D"#954F72"> <div class=3D"WordSection1"> Dear list,<o:p></o:p> <o:p> </o:p> We have developed several model= s allowing to predict speech intelligibility in noise and reverberation. Mo= st of them are using as inputs the signals at the listener’s ears (so= me use binaural room impulse responses) to predict differences in speech reception threshold between different condit= ions. There are different model versions that predict different effects: bi= naural hearing (spatial release from masking), dip listening, the effect of= hearing loss (taking the listener’s audiogram as additional input), multiple effects of reverberation, and har= monic cancellation. <o:p></o:p> You can find them here: = <a href=3D"https://mathieulavandier.wordpress.com/home/models/">https://mathieulavandier.wordpress.com/home/models/</a><s= pan lang=3D"EN-US"><o:p></o:p> With each model, there is an ex= ample of the predictions corresponding to one dataset from the literature. = You have access to the signals used in the speech intelligibility test, alo= ng with the data resulting from this test (listeners’ SRTs), and the code used to run the model on this d= ataset; so that you can check how to handle a model before using it to pred= ict intelligibility in other conditions.<o:p></o:p> <o:p> </o:p> Do not hesitate to play around = with these models and give us feedback! We hope they can be useful.<o:p></o= :p> <o:p> </o:p> All the best,<o:p></o:p>= mat<o:p></o:p> <o:p> </o:p> ------------------------------------------------------= -----------------------------------------<o:p></o:p> Mathieu Lavandier<o:p></o:p> <a href=3D"https://mathieulavandier.wordpress.com/"><s= pan style=3D"color:#0563C1">https://mathieulavandier.wordpress.com/<= /a> Universit=E9 de Lyon, Labex CeLyA<o:p></o:p> <a href=3D"https://celya.universite-lyon.fr/">https://celya.universite-lyon.fr</a><o:p></o:p> ENTPE, Laboratoire de Tribologie et Dynamique des Syst= =E8mes (LTDS, UMR 5513)<o:p></o:p> Rue M. Audin, 69518 Vaulx-en-Velin Cedex, FRANCE T=E9l : +33 (0)4 72 04 70 30<o:p></o:p> <o:p> </o:p> </div> </body> </html> --_000_bd083ae02cc94456b84528253ad33803entpefr_--

This message came from the mail archive
postings/2026/
maintained by:

DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University