Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuhn, Korbinian, Kersken, Verena, Zimmermann, Gottfried
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917779767033856
author Kuhn, Korbinian
Kersken, Verena
Zimmermann, Gottfried
author_facet Kuhn, Korbinian
Kersken, Verena
Zimmermann, Gottfried
contents The Word Error Rate (WER) is the common measure of accuracy for Automatic Speech Recognition (ASR). Transcripts are usually pre-processed by substituting specific characters to account for non-semantic differences. As a result of this normalisation, information on the accuracy of punctuation or capitalisation is lost. We present a non-destructive, token-based approach using an extended Levenshtein distance algorithm to compute a robust WER and additional orthographic metrics. Transcription errors are also classified more granularly by existing string similarity and phonetic algorithms. An evaluation on several datasets demonstrates the practical equivalence of our approach compared to common WER computations. We also provide an exemplary analysis of derived use cases, such as a punctuation error rate, and a web application for interactive use and visualisation of our implementation. The code is available open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15616
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications
Kuhn, Korbinian
Kersken, Verena
Zimmermann, Gottfried
Computation and Language
Sound
Audio and Speech Processing
I.2.7
The Word Error Rate (WER) is the common measure of accuracy for Automatic Speech Recognition (ASR). Transcripts are usually pre-processed by substituting specific characters to account for non-semantic differences. As a result of this normalisation, information on the accuracy of punctuation or capitalisation is lost. We present a non-destructive, token-based approach using an extended Levenshtein distance algorithm to compute a robust WER and additional orthographic metrics. Transcription errors are also classified more granularly by existing string similarity and phonetic algorithms. An evaluation on several datasets demonstrates the practical equivalence of our approach compared to common WER computations. We also provide an exemplary analysis of derived use cases, such as a punctuation error rate, and a web application for interactive use and visualisation of our implementation. The code is available open-source.
title Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications
topic Computation and Language
Sound
Audio and Speech Processing
I.2.7
url https://arxiv.org/abs/2408.15616