SII: Speech Intelligibility Index
NEWS:
Google has just released a Python implementation of the standard SII protocol. Furthermore, there is a Colab that demonstrates how to use the SII code. In particular it shows how to compute the SII in the face of hearing loss, reverberation, and listening to the radio in the car. The code is published on GitHub.
https://github.com/google/speech_intelligibility_index
The colab is open source and can be used by anybody on the web. It imports the SII code from GitHub, and shows how to use it.
https://colab.research.google.com/drive/18tYuhyMHAcJT9wfZLvtCVZ7TKNiMJ-vo?usp=sharingGoogle has
This site has been created by members of the Acoustical Society of America (ASA) Working Group S3-79, which is in charge of reviewing American National Standard ANSI S3.5-1997 (“Methods for Calculation of the Speech Intelligibility Index”).
The standard defines a method for computing a physical measure that is highly correlated with the intelligibility of speech as evaluated by speech perception tests given a group of talkers and listeners. This measure is called the Speech Intelligibility Index, or SII. The SII is calculated from acoustical measurements of speech and noise.
The site provides software for calculating the Speech Intelligibility Index (SII), as well as notes relevant to potential future changes of the standard and the listing of known errors to be corrected in the next version of the standard. You are encouraged to contact us with any information that may help make the Standard better and easier to use. Also, if you have other software that can facilitate SII calculations, we urge you to send it to us for a review and posting on this site.
The fundamental concepts of the standardized SII index are discussed in detail in
Pavlovic, C.V. (1987) "Derivation of primary parameters and procedures for use in speech intelligibility predictions," J. Acoust. Soc. Am. 82, 413-422.
The current members of the ASA Writing Group S3-79 are:
Caslav (Chas) Pavlovic, Ph.D., BatAndCat Corporation, Chairman S3-79.
Ben Hornsby, Ph.D., Vanderbilt University
John Hou, Ph.D., Amazon.com Inc
Hannes Muesch, Ph.D., Dolby Laboratories
Koenraad Rhebergen, PhD., Head & Neck Surgery, University Medical Center Utrecht
This site is made possible by funding from BatAndCat Corporation.
Google has just released a Python implementation of the standard SII protocol. Furthermore, there is a Colab that demonstrates how to use the SII code. In particular it shows how to compute the SII in the face of hearing loss, reverberation, and listening to the radio in the car. The code is published on GitHub.
https://github.com/google/speech_intelligibility_index
The colab is open source and can be used by anybody on the web. It imports the SII code from GitHub, and shows how to use it.
https://colab.research.google.com/drive/18tYuhyMHAcJT9wfZLvtCVZ7TKNiMJ-vo?usp=sharingGoogle has
This site has been created by members of the Acoustical Society of America (ASA) Working Group S3-79, which is in charge of reviewing American National Standard ANSI S3.5-1997 (“Methods for Calculation of the Speech Intelligibility Index”).
The standard defines a method for computing a physical measure that is highly correlated with the intelligibility of speech as evaluated by speech perception tests given a group of talkers and listeners. This measure is called the Speech Intelligibility Index, or SII. The SII is calculated from acoustical measurements of speech and noise.
The site provides software for calculating the Speech Intelligibility Index (SII), as well as notes relevant to potential future changes of the standard and the listing of known errors to be corrected in the next version of the standard. You are encouraged to contact us with any information that may help make the Standard better and easier to use. Also, if you have other software that can facilitate SII calculations, we urge you to send it to us for a review and posting on this site.
The fundamental concepts of the standardized SII index are discussed in detail in
Pavlovic, C.V. (1987) "Derivation of primary parameters and procedures for use in speech intelligibility predictions," J. Acoust. Soc. Am. 82, 413-422.
The current members of the ASA Writing Group S3-79 are:
Caslav (Chas) Pavlovic, Ph.D., BatAndCat Corporation, Chairman S3-79.
Ben Hornsby, Ph.D., Vanderbilt University
John Hou, Ph.D., Amazon.com Inc
Hannes Muesch, Ph.D., Dolby Laboratories
Koenraad Rhebergen, PhD., Head & Neck Surgery, University Medical Center Utrecht
This site is made possible by funding from BatAndCat Corporation.