mlsanityData to 7 Oct 2026

Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Text

arXiv 2310.08225 ↗First posted 12 Oct 2023eess.AS cs.CL cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

Word error rate (WER) estimation aims to evaluate the quality of an automatic speech recognition (ASR) system's output without requiring ground-truth labels. This task has gained increasing attention as advanced ASR systems are trained on large amounts of data. In this context, the computational efficiency of a WER estimator becomes essential in practice. However, previous works have not prioritised this aspect. In this paper, a Fast estimator for WER (Fe-WER) is introduced, utilizing average pooling over self-supervised learning representations for speech and text. Our results demonstrate that Fe-WER outperformed a baseline relatively by 14.10% in root mean square error and 1.22% in Pearson correlation coefficient on Ted-Lium3. Moreover, a comparative analysis of the distributions of target WER and WER estimates was conducted, including an examination of the average values per speaker. Lastly, the inference speed was approximately 3.4 times faster in the real-time factor.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

23 of 34 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  8. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  9. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  10. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  11. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  12. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
11 more
  1. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  2. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  3. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  4. 2019Self-Training for End-to-End Speech Recognitioncited by 128
  5. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 98
  6. 2020Semi-supervised ASR by End-to-end Self-trainingcited by 29
  7. 2020Word Error Rate Estimation Without ASR Output: e-WER2cited by 8
  8. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 7
  9. 2019On Modeling ASR Word Confidencecited by 6
  10. 2022MTI-Net: A Multi-Target Speech Intelligibility Prediction Modelcited by 6
  11. 2023Multilingual Word Error Rate Estimation: e-WER3cited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2024Automatic Speech Recognition System-Independent Word Error Rate Estimationcited by 2
  2. 2026Multimodal Consistency-Guided Reference-Free Data Selection for ASR Accent Adaptationcited by 0
  3. 2026Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancycited by 0
  4. 2026Audio LLMs Know When They Can't Hear Youcited by 0