# Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR

arXiv: https://arxiv.org/abs/2609.20828 · HTML: https://mlsanity.com/paper/2609.20828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR](https://mlsanity.com/paper/2406.06619/) (2024)
- [Retrieval Augmented Correction of Named Entity Speech Recognition Errors](https://mlsanity.com/paper/2409.06062/) (2024)
- [Augmenting Automatic Speech Recognition Models with Disfluency Detection](https://mlsanity.com/paper/2409.10177/) (2024)
- [Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition](https://mlsanity.com/paper/2505.20006/) (2025)
- [Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning](https://mlsanity.com/paper/2506.21576/) (2025)
- [WhisperNER: Unified Open Named Entity and Speech Recognition](https://mlsanity.com/paper/2409.08107/) (2024)
- [WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper](https://mlsanity.com/paper/2505.21551/) (2025)
- [Customizing Speech Recognition Model with Large Language Model Feedback](https://mlsanity.com/paper/2506.11091/) (2025)

## Abstract (arXiv)

ASR systems optimised for Word Error Rate (WER) often miss named entities and filled pauses in accented conversational English, both critical for language-learning feedback. We present a three-stage pipeline for speakers from India, Indonesia, and Latin America: (1) heuristic SQL filters curating entity-rich training data at 2.8x the entity density of random sampling, (2) regional LoRA adapters fine-tuned on Qwen2.5-Omni-3B producing both verbatim and corrected transcripts in a single forward pass, and (3) a six-category error taxonomy validated by an LLM-based judge (83.8% agreement, 210 human-labelled samples). The pipeline achieves 80-85% entity recall (up from 53-55%), 76-86% filler recall (up from <5%), and 6-10% WER across 6k test utterances, outperforming Whisper and a commercial ASR on entity recall while matching a zero-shot 30B model with 10x fewer parameters. Paired bootstrap tests confirm that curation alone accounts for 2.8-4.2 pp of entity recall gain (p<0.0001).