Word error rate



Word error rate (WER) is a common metric of the performance of a
speech recognition Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
machine translation Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation), is a sub-field of computational linguistics that investigates th ...
system. The general difficulty of measuring performance lies in the fact that the recognized word sequence can have a different length from the reference word sequence (supposedly the correct one). The WER is derived from the
Levenshtein distance In information theory, linguistics, and computer science, the Levenshtein distance is a string metric for measuring the difference between two sequences. Informally, the Levenshtein distance between two words is the minimum number of single-cha ...
, working at the word level instead of the
phoneme In phonology and linguistics, a phoneme () is a unit of sound that can distinguish one word from another in a particular language. For example, in most dialects of English, with the notable exception of the West Midlands and the north-w ...
level. The WER is a valuable tool for comparing different systems as well as for evaluating improvements within one system. This kind of measurement, however, provides no details on the nature of translation errors and further work is therefore required to identify the main source(s) of error and to focus any research effort. This problem is solved by first aligning the recognized word sequence with the reference (spoken) word sequence using dynamic string alignment. Examination of this issue is seen through a theory called the power law that states the correlation between perplexity and word error rate. Word error rate can then be computed as: : \mathit = \frac = \frac where * ''S'' is the number of substitutions, * ''D'' is the number of deletions, * ''I'' is the number of insertions, * ''C'' is the number of correct words, * ''N'' is the number of words in the reference (N=S+D+C) The intuition behind 'deletion' and 'insertion' is how to get from the reference to the hypothesis. So if we have the reference "This is wikipedia" and hypothesis "This _ wikipedia", we call it a deletion. When reporting the performance of a speech recognition system, sometimes ''word accuracy (WAcc)'' is used instead: : \mathit = 1 - \mathit = \frac = \frac 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.


It is commonly believed that a lower word error rate shows superior accuracy in recognition of speech, compared with a higher word error rate. However, at least one study has shown that this may not be true. In a
Microsoft Research Microsoft Research (MSR) is the research subsidiary of Microsoft. It was created in 1991 by Richard Rashid, Bill Gates and Nathan Myhrvold with the intent to advance state-of-the-art computing and solve difficult world problems through technol ...
experiment, it was shown that, if people were trained under "that matches the optimization objective for understanding", (Wang, Acero and Chelba, 2003) they would show a higher accuracy in understanding of language than other people who demonstrated a lower word error rate, showing that true understanding of spoken language relies on more than just high word recognition accuracy.

Other metrics

One problem with using a generic formula such as the one above, however, is that no account is taken of the effect that different types of error may have on the likelihood of successful outcome, e.g. some errors may be more disruptive than others and some may be corrected more easily than others. These factors are likely to be specific to the syntax being tested. A further problem is that, even with the best alignment, the formula cannot distinguish a substitution error from a combined deletion plus insertion error. Hunt (1990) has proposed the use of a weighted measure of performance accuracy where errors of substitution are weighted at unity but errors of deletion and insertion are both weighted only at 0.5, thus: : \mathit = \frac{N} There is some debate, however, as to whether Hunt's formula may properly be used to assess the performance of a single system, as it was developed as a means of comparing more fairly competing candidate systems. A further complication is added by whether a given syntax allows for error correction and, if it does, how easy that process is for the user. There is thus some merit to the argument that performance metrics should be developed to suit the particular system being measured. Whichever metric is used, however, one major theoretical problem in assessing the performance of a system is deciding whether a word has been “mis-pronounced,” i.e. does the fault lie with the user or with the recogniser. This may be particularly relevant in a system which is designed to cope with non-native speakers of a given language or with strong regional accents. The pace at which words should be spoken during the measurement process is also a source of variability between subjects, as is the need for subjects to rest or take a breath. All such factors may need to be controlled in some way. For text dictation it is generally agreed that performance accuracy at a rate below 95% is not acceptable, but this again may be syntax and/or domain specific, e.g. whether there is time pressure on users to complete the task, whether there are alternative methods of completion, and so on. The term "Single Word Error Rate" is sometimes referred to as the percentage of incorrect recognitions for each different word in the system vocabulary.

Edit distance

The word error rate may also be referred to as the length normalized edit distance. The normalized edit distance between X and Y, ''d''( X, Y ) is defined as the minimum of W( P ) / L ( P ), where P is an editing path between X and Y, W ( P ) is the sum of the weights of the elementary edit operations of P, and L(P) is the number of these operations (length of P).Computation of Normalized Edit Distance and Application:AndrCs Marzal and Enrique Vidal

See also

BLEU Bleu or BLEU may refer to: * the French word for blue * '' Three Colors: Blue'', a 1993 movie * BLEU (Bilingual Evaluation Understudy), a machine translation evaluation metric * Belgium–Luxembourg Economic Union * Blue cheese, a type of chee ...
F-Measure In statistical analysis of binary classification, the F-score or F-measure is a measure of a test's accuracy. It is calculated from the precision and recall of the test, where the precision is the number of true positive results divided by the n ...
METEOR A meteoroid () is a small rocky or metallic body in outer space. Meteoroids are defined as objects significantly smaller than asteroids, ranging in size from grains to objects up to a meter wide. Objects smaller than this are classified as mi ...
NIST (metric) NIST is a method for evaluating the quality of text which has been translated using machine translation. Its name comes from the US National Institute of Standards and Technology. It is based on the BLEU metric, but with some alterations. Where ...
ROUGE (metric) ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics and a software package used for evaluating automatic summarization and machine translation software in natural language processing. The metrics compare an automatical ...



Other sources

McCowan et al. 2005: ''On the Use of Information Retrieval Measures for Speech Recognition Evaluation''

Hunt, M.J., 1990: ''Figures of Merit for Assessing Connected Word Recognisers'' (Speech Communication, 9, 1990, pp 239-336)

Zechner, K., Waibel, A.''Minimizing Word Error Rate in Textual Summaries of Spoken Language''
Speech recognition Machine translation Evaluation of machine translation Rates