Glossary
- ASR : Automated Speech Recognition
- OOG : Out Of Grammar - real spoken utterance is outside of the set of utterances generate/recognized by the grammar. It is impossible to recognize this utterance using the grammar.
- IG - In Grammar : real spoken utterance falls within the grammar, i.e. it can be recognized by the grammar. If it does not get recognized it is because the ASR had problem with the way it was said, noise, volume, audio quality, etc.
- NM - No Match : ASR could not recognizer the spoken utterance either due to it being OOG or some ASR recognition issue.
- TN - True Negative (Correct Rejection) : OOG utterance was correctly not recognized
- FP - False(ly) Positive (False Alarm) : OOG utterance was incorrectly recognized as some in-grammar utterance
- N = TN + FP : Negative Outcomes
- TP - True Positive (Hit) : In-Grammar utterance was correctly recognized
- WP - Wrong Positive (misclassified) : In-Grammar utterance was recognized wrongly as some other In-Grammar utterance
- FN - False Negative (Miss) : In-Grammar utterance was rejected - this can have several causes:
- there was No Match
- utterance was given __garbage__ tag by the grammar
- confidence of recognition was below acceptance threshold
- P = TP + WP + FN : Positive Outcomes
- Precision = TP / (TP + WP + FP) : https://en.wikipedia.org/wiki/Precision_and_recall#Precision
- Recall = TP / P : https://en.wikipedia.org/wiki/Precision_and_recall#Recall
- Accuracy (A) = (TP + TN) / (P + N) : https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification
- F1 score (F) = 2*P*R / (P+R) [a harmonic mean of Precision and Recall] : https://en.wikipedia.org/wiki/Precision_and_recall#F-measure
- Total Error = (FP + WP + FN) / (P + N)
Table of Outcomes
True Classification | Positive / Negative | Recognizer Outcome | Outcome Category if below or equal threshold |
Outcome Category if above threshold |
OOG | N | OOG or NM | TN | TN |
OOG | N | IG (always incorrect) |
TN | FP (OOG has been accepted as IG) |
IG | P | OOG or NM | FN | FN |
IG | P | IG incorrect | FN | WP (IG has been misclassified) |
IG | P | IG correct | FN | TP |
If threshold is 0 (min) we have the following categories:
- Out of Negative
- TN : this will be the lowest possible TN value
- FP (all OOG that are recognized as IG) : this will be the highest possible FP value
- Out of Positive
- TP : highest possible TP value
- WP - highest possible WP value
- FN (if classified as OOG/NM) : lowest possible FN value
If threshold is 100 (max) the we will have only:
- Out of Negative:
- TN
- Out of Positive:
- FN
Charts
Total Operating Characteristics
You can learn more about this type of chart from this wikipedia article: https://en.wikipedia.org/wiki/Total_operating_characteristic
Mapping of the terminology from the wikipedia to the terminology use by us is as follows (Wiki -> us):
- False Alarm -> False Positive (FP)
- Hit -> True Positive (TP)
- Miss -> False Negative (FN)
- Correct Rejection -> True Negative (TN)
In our chart we are additionally adding Wrong Positive between Hit and Miss
Comments
0 comments
Please sign in to leave a comment.