mlsanityData to 7 Oct 2026

Multilingual Word Error Rate Estimation: e-WER3

arXiv 2304.00649 ↗First posted 2 Apr 2023cs.CL cs.LG cs.SDcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 2 Apr 2023.

Builds on

12 of 21 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  5. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  6. 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79
  7. 2016Achieving Human Parity in Conversational Speech Recognitioncited by 63
  8. 2017English Conversational Telephone Speech Recognition by Humans and Machinescited by 40
  9. 2021Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASRcited by 40
  10. 2021QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpuscited by 38
  11. 2020Word Error Rate Estimation Without ASR Output: e-WER2cited by 8
  12. 2019Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition Systemcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 1.

5 papers.

  1. 2023Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Textcited by 4
  2. 2024Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metriccited by 4
  3. 2023Big model only for hard audios: Sample dependent Whisper model selection for efficient inferencescited by 2
  4. 2024Automatic Speech Recognition System-Independent Word Error Rate Estimationcited by 2
  5. 2025On the Robust Approximation of ASR Metricscited by 2