# When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents

arXiv: https://arxiv.org/abs/2610.17619 · HTML: https://mlsanity.com/paper/2610.17619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://mlsanity.com/paper/1909.02188/) (2019)
- [SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities](https://mlsanity.com/paper/2203.06849/) (2022)
- [SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech](https://mlsanity.com/paper/2111.10367/) (2021)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [VoiceAgentBench: Are Voice Assistants ready for agentic tasks?](https://mlsanity.com/paper/2510.07978/) (2025)
- [EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents](https://mlsanity.com/paper/2605.13841/) (2026)
- [Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability](https://mlsanity.com/paper/2106.02016/) (2021)
- [Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks](https://mlsanity.com/paper/2502.13645/) (2025)
- [From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents](https://mlsanity.com/paper/2605.15104/) (2026)

## Abstract (arXiv)

In cascaded voice agents, ASR errors can have markedly different downstream consequences: a small transcription error may leave a tool call unchanged or alter its intent or arguments. Conventional word error rate (WER), however, does not capture these differences. We introduce SpeechEvalX, a paired diagnostic protocol that evaluates how task roles affected by ASR errors influence structured tool calls. Controlled edits are matched by source utterance, edit count, and operation, while task-role labels are compared with lexical severity, BERT cosine distance, Semantic-WER, and binary criticality. Across 594 source utterances, joint call accuracy falls from 82.3% with reference transcripts to 71.9-74.9% across three ASR front ends. Number and negation edits cause 21.9-25.7 percentage-point losses, versus 1.4-2.9 points for control edits. Detailed task-role labels improve source-grouped ROC-AUC from 0.73 to 0.78 over binary criticality, showing that downstream impact depends strongly on the task role affected.