article · 2023
Multilingual Word Error Rate Estimation: E-Wer3
Shammur Absar Chowdhury, Ahmed Ali
Cited by 6Abstract and details only
Abstract
The success of the multilingual automatic speech recognition systems empowered many voice-driven applications. However, measuring the performance of such systems remains a major challenge, due to its dependency on manually transcribed speech data in both mono- and multilingual scenarios. In this paper, we propose a novel multilingual framework – eWER3 – jointly trained on acoustic and lexical representation to estimate word error rate. We demonstrate the effectiveness of eWER3 to (i) predict WER without using any internal states from the ASR and (ii) use the multilingual shared latent space to push the performance of the close-related languages. We show our proposed multilingual model outperforms the previous monolingual word error rate estimation method (eWER2) by an absolute 9% increase in Pearson correlation coefficient (PCC), with better overall estimation between the predicted and reference WER.
Cite this paper
Chowdhury, S. A., & Ali, A. (2023). Multilingual Word Error Rate Estimation: E-Wer3. https://doi.org/10.1109/icassp49357.2023.10095888
Chowdhury, Shammur Absar, and Ahmed Ali. “Multilingual Word Error Rate Estimation: E-Wer3.” 2023, pp. 1–5, https://doi.org/10.1109/icassp49357.2023.10095888.
Chowdhury, Shammur Absar, and Ahmed Ali. 2023. “Multilingual Word Error Rate Estimation: E-Wer3.” https://doi.org/10.1109/icassp49357.2023.10095888.
Chowdhury, S.A. and Ali, A. (2023) ‘Multilingual Word Error Rate Estimation: E-Wer3’. Available at: https://doi.org/10.1109/icassp49357.2023.10095888.
@article{chowdhury2023multilingual,
title = {{Multilingual Word Error Rate Estimation: E-Wer3}},
author = {Chowdhury, Shammur Absar and Ali, Ahmed},
pages = {1--5},
year = {2023},
doi = {10.1109/icassp49357.2023.10095888}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.