Expert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeus

Richard Rose
10/19/2026
cs.CLcs.SD

No official code found. Best implementation: cburst/oollim (0 stars, last commit 2026-10-20).

Abstract

oollim is a locally executable system for evaluating L2 English pronunciation accuracy, fluency, and prosody on a consumer computer. The system combines pretrained XLS-R, XEUS, and PhoneticXeus representations with reference-text features and ridge regressions trained on SpeechOcean762, the Korean Learners' L2 Speech Corpus (English), J-AESOP, and their combinations. On 305 independently held-out recordings assessed by three expert raters, several ridge configurations substantially outperform archived Azure API scores obtained in January 2026 in both Spearman correlation and quadratic weighted kappa across all three constructs. These results support expert speech evaluation on consumer hardware using pretrained representations and construct-specific regressions, without neural-model fine-tuning or calibration on the private evaluation data.

View on arXivView PDF

Code Implementations(1)

cburst/oollimCommunity73%

Expert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeus

00Oct 18, 2026todayNOASSERTION

Similar Papers

Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal

82% match2026

Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment

80% match2023

Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India

79% match2026

NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning

79% match1 repo192023

SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation

79% match2026

English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM

79% match2025

Cite this paper

@article{rose2026expert,
  title  = {Expert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeus},
  author = {Richard Rose},
  year   = {2026},
  eprint = {2610.26406},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2610.26406v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2610.26406.svg)](https://codeofpaper.com/paper/2610.26406)

Discussion