FLUCALC words/minute computation

[Brian Macwhinney]

Dear Tracy,
    
This is noted in the manual, where it says on page 139, "If the sample has been processed for ASR (automatic speech recognition) using the batchalign system at https://github.com/talkbank there will be a new %wor line that can be used when the +a switch is selected to derive more accurate times for word and pause duration. These additional times are then summarized in 9 columns are the end of the output.”
  
If you were using an older version of the manual, that might be missing.

Best,

— Brian MacWhinney
Teresa Heinz Professor of Cognitive Psychology, 
Language Technologies and Modern Languages, CMU 

> On Oct 25, 2024, at 3:16 PM, Tracy Preza <tpreza2 at illinois.edu> wrote:
> 
> Hello, 
> We are exploring the fluency measures computed automatically through FLUCALC, and have questions about how exactly FLUCALC computes words per minute and syllable per minute. We haven’t been able to find this in the manual or published articles. The denominator doesn’t seem to be based on the overall elapsed time, but we can’t verify if it is based on the elapsed time from bullet to bullet for each speaker. Could you point us to what information FLUCALC is pulling for these measures?
> 
> Thank you! 
> Tracy
> 
> 
> -- 
> You received this message because you are subscribed to the Google Groups "chibolts" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
> To view this discussion visit https://groups.google.com/d/msgid/chibolts/09efe29a-5b5c-4609-b51d-99d11646e63fn%40googlegroups.com.

-- 
You received this message because you are subscribed to the Google Groups "chibolts" group.
To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/chibolts/8637B7FC-9E67-40B7-ADC2-624279AD526A%40andrew.cmu.edu.