HResults: Dynamic Programming

[Vishnu M]

I don’t quite understand this complicated methodology that HResults is using to estimate accuracy/WER. I thought it was just plain accuracy i.e. is label same or not divided by total labels to be predicted.

Could you please explain what this attachment is saying a little?

Attachments:

You must be logged in to view attached files.

[Simon]

HResults uses dynamic programming to align the recognition output and the reference transcription. So, WER is simply the edit distance between recognition output and reference transcription.

There are three possible types of error: substitutions, insertions and deletions. WER is just the sum of those three, divided by the number of words in the reference transcription, and expressed as a percentage.

For the special case of isolated words, the only possible type of error is a substitution error, and the dynamic programming is not really needed.

Note that HResults reports “Accuracy (Acc)”, but you should only use WER (100 – Acc) in your report.

Ignore the value of “Correct (Corr)” reported by HResults – this does not account for insertion errors and is not a measure used anymore.

[Author]

Posts