ASR-Free Pronunciation Assessment
Not on the map. Why?
Abstract (arXiv)
Most of the pronunciation assessment methods are based on local features derived from automatic speech recognition (ASR), e.g., the Goodness of Pronunciation (GOP) score. In this paper, we investigate an ASR-free scoring approach that is derived from the marginal distribution of raw speech signals. The hypothesis is that even if we have no knowledge of the language (so cannot recognize the phones/words), we can still tell how good a pronunciation is, by comparatively listening to some speech data from the target language. Our analysis shows that this new scoring approach provides an interesting correction for the phone-competition problem of GOP. Experimental results on the ERJ dataset demonstrated that combining the ASR-free score and GOP can achieve better performance than the GOP baseline.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 May 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 3; 2023: 2; 2024: 0; 2025: 1; 2026: 1.
12 papers.
- 2022Proficiency assessment of L2 spoken English using wav2vec 2.0cited by 20
- 2021Multilingual Speech Evaluation: Case Studies on English, Malay and Tamilcited by 10
- 2023Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantificationcited by 10
- 2021Mispronunciation Detection in Non-native (L2) English with Uncertainty Modelingcited by 5
- 2021Weakly-supervised word-level pronunciation error detection in non-native English speechcited by 4
- 2022Computer-assisted Pronunciation Training -- Speech synthesis is almost all you needcited by 4
- 2022L2 proficiency assessment using self-supervised speech representationscited by 4
- 2023Addressing Cold Start Problem for End-to-end Automatic Speech Scoringcited by 3
- 2021Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanismscited by 2
- 2025Automated evaluation of children's speech fluency for low-resource languagescited by 1
- 2021Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosiscited by 0
- 2026Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessmentcited by 0
- 2026Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment5 Jan 2026
- 2025Automated evaluation of children's speech fluency for low-resource languages26 May 2025
- 2023Addressing Cold Start Problem for End-to-end Automatic Speech Scoring25 Jun 2023
- 2023Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification28 May 2023
- 2022L2 proficiency assessment using self-supervised speech representations16 Nov 2022
- 2022Proficiency assessment of L2 spoken English using wav2vec 2.024 Oct 2022
- 2022Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need2 Jul 2022
- 2021Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosis1 Nov 2021
- 2021Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms17 Oct 2021
- 2021Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil8 Jul 2021
- 2021Weakly-supervised word-level pronunciation error detection in non-native English speech7 Jun 2021
- 2021Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling16 Jan 2021