mlsanityData to 7 Oct 2026

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't

arXiv 2406.09202 ↗First posted 13 Jun 2024cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We investigate what linguistic factors affect the performance of Automatic Speech Recognition (ASR) models. We hypothesize that orthographic and phonological complexities both degrade accuracy. To examine this, we fine-tune the multilingual self-supervised pretrained model Wav2Vec2-XLSR-53 on 25 languages with 15 writing systems, and we compare their ASR accuracy, number of graphemes, unigram grapheme entropy, logographicity (how much word/morpheme-level information is encoded in the writing system), and number of phonemes. The results demonstrate that orthographic complexities significantly correlate with low ASR accuracy, while phonological complexity shows no significant correlation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 13 Jun 2024.

Builds on

10 of 20 references.

References · 10

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  6. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  7. 2020A Large-Scale Chinese Short-Text Conversation Datasetcited by 77
  8. 2023PyThaiNLP: Thai Natural Language Processing in Pythoncited by 27
  9. 2023Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languagescited by 20
  10. 2013Rank-frequency relation for Chinese characterscited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliterationcited by 3
  2. 2026Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varietiescited by 2
  3. 2026Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoancited by 0
  4. 2026Pretrained self-supervised speech models can recognize unseen consonantscited by 0