mlsanityData to 7 Oct 2026

Goodness-of-pronunciation without phoneme time alignment

arXiv 2603.25150 ↗First posted 26 Mar 2026cs.CL cs.AI cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

In speech evaluation, an Automatic Speech Recognition (ASR) model often computes time boundaries and phoneme posteriors for input features. However, limited data for ASR training hinders expansion of speech evaluation to low-resource languages. Open-source weakly-supervised models are capable of ASR over many languages, but they are frame-asynchronous and not phonemic, hindering feature extraction for speech evaluation. This paper proposes to overcome incompatibilities for feature extraction with weakly-supervised models, easing expansion of speech evaluation to low-resource languages. Phoneme posteriors are computed by mapping ASR hypotheses to a phoneme confusion network. Word instead of phoneme-level speaking rate and duration are used. Phoneme and frame-level features are combined using a cross-attention architecture, obviating phoneme time alignment. This performs comparably with standard frame-synchronous features on English speechocean762 and low-resource Tamil datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 41 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

17 of 41 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  6. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  7. 2015Listen, Attend and Spellcited by 542
  8. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  9. 2021speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessmentcited by 57
  10. 2022Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessmentcited by 36
  11. 2022Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learningcited by 29
  12. 20223M: An Effective Multi-view, Multi-granularity, and Multi-aspect Modeling Approach to English Pronunciation Assessmentcited by 21
5 more
  1. 2022Proficiency assessment of L2 spoken English using wav2vec 2.0cited by 20
  2. 2023Adapting an ASR Foundation Model for Spoken Language Assessmentcited by 14
  3. 2021Multilingual Speech Evaluation: Case Studies on English, Malay and Tamilcited by 10
  4. 2023Zero-Shot Automatic Pronunciation Assessmentcited by 5
  5. 2023End-to-End Word-Level Pronunciation Assessment with MASK Pre-trainingcited by 4

Built on by

Not cited yet.