Take the 2-minute tour ×
English Language & Usage Stack Exchange is a question and answer site for linguists, etymologists, and serious English language enthusiasts. It's 100% free, no registration required.

The Flesch Kincaid readability test is a measure of a written document's readability. There are numerous methods of measuring written text's readability but processing spoken text is different than written text. Is there a similar way to measure spoken text but with the auditory reception of speech taken into account as opposed to the visual reception of written communication?

share|improve this question

closed as off topic by FumbleFingers, onomatomaniak, kiamlaluno, simchona, Daniel Dec 19 '11 at 19:08

Questions on English Language & Usage Stack Exchange are expected to relate to English language and usage within the scope defined by the community. Consider editing the question or leaving comments for improvement if you believe the question can be reworded to fit within the scope. Read more about reopening questions here.If this question can be reworded to fit the rules in the help center, please edit the question.

2 Answers 2

up vote 1 down vote accepted

There's also the similar 'Gunning Fog Index' (see here, for example), and probably several others. The nature of speech would make it much more difficult to analyze it in this way, not least because of the role of paralanguage. Any test of intelligibility would ulttimately rely on some kind of transcript, whose analysis would in part, at least, have to rely on the kind of tests applied to written language.

share|improve this answer
    
I have transcripts of the spoken language but it felt wrong to utilize measures that are designed for written communication on spoken communication that happens to be captured in written form. I'm attempting to develop quantitative techniques to augment discourse analysis and this may be a useful avenue. –  Tyler Rinker Dec 19 '11 at 14:16

Speech recognition has yet not delivered on its promise, to the extent it could be applied effectively in most cases. I believe lots of potential applications are hindered for want of a real and powerful speech engine.

share|improve this answer
1  
It would be sufficient to have a test that analysed a transcript of the speech. With the right markup, a human with computer assistance could produce a transcription complete with inflection, pauses, interjections. Then some algorithm could test that for "listenability" –  slim Dec 19 '11 at 13:08

Not the answer you're looking for? Browse other questions tagged or ask your own question.