article · 2018
Word Error Rate Estimation for Speech Recognition: e-WER
Cited by 114Open access
Abstract
Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive. In this paper, we propose a novel approach to estimate WER, or e-WER, which does not require a gold-standard transcription of the test set. Our e-WER framework uses a comprehensive set of features: ASR recognised text, character recognition results to complement recognition output, and internal decoder features. We report results for the two features; black-box and glass-box using unseen 24 Arabic broadcast programs. Our system achieves 16.9% WER root mean squared error (RMSE) across 1,400 sentences. The estimated overall WER e-WER was 25.3% for the three hours test set, while the actual WER was 28.5%.
Cite this paper
Ali, A., & Renals, S. (2018). Word Error Rate Estimation for Speech Recognition: e-WER. https://doi.org/10.18653/v1/p18-2004
Ali, Ahmed, and Steve Renals. “Word Error Rate Estimation for Speech Recognition: e-WER.” 2018, pp. 20–24, https://doi.org/10.18653/v1/p18-2004.
Ali, Ahmed, and Steve Renals. 2018. “Word Error Rate Estimation for Speech Recognition: e-WER.” https://doi.org/10.18653/v1/p18-2004.
Ali, A. and Renals, S. (2018) ‘Word Error Rate Estimation for Speech Recognition: e-WER’. Available at: https://doi.org/10.18653/v1/p18-2004.
@article{ali2018word,
title = {{Word Error Rate Estimation for Speech Recognition: e-WER}},
author = {Ali, Ahmed and Renals, Steve},
pages = {20--24},
year = {2018},
doi = {10.18653/v1/p18-2004}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.