Word Accuracy (WAcc) Measure

A Word Accuracy (WAcc) Measure is a Performance Metric that is directly related to the WER as: $WAcc=1-WER$.

• Example(s):
  • ...
  • …
• Counter-Example(s):
  • Word Error Rate,
  • F-Measure,
  • METEOR Metric,
  • ROUGE Metric,
  • NIST Metric,
  • PER Metric,
  • BLEU Score .
• See: Phoneme, Speech Recognition, Machine Translation, Levenshtein Distance, Phonetic Levenshtein Distance, ASR Latency.

---

---

References

2021

• (Wikipedia, 2021) ⇒ https://en.wikipedia.org/wiki/Word_error_rate Retrieved:2021-6-20.
  • (...) When reporting the performance of a speech recognition system, sometimes word accuracy (WAcc) is used instead:

    [math]\displaystyle{ \mathit{WAcc} = 1 - \mathit{WER} = \frac{N-S-D-I}{N} = \frac{C-I}{N} }[/math] Note that since N is the number of words in the reference, the word error rate can be larger than 1.0, and thus, the word accuracy can be smaller than 0.0.

---