# VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2608.28916 · HTML: https://mlsanity.com/paper/2608.28916/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models](https://mlsanity.com/paper/2310.02943/) (2023)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark](https://mlsanity.com/paper/2507.05727/) (2025)
- [Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability](https://mlsanity.com/paper/2106.02016/) (2021)
- [Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition](https://mlsanity.com/paper/2210.15063/) (2022)

## Abstract (arXiv)

Automatic speech recognition is usually evaluated with word error rate (WER), although voice workflows often require exact written values. VoiceCodeBench measures whether transcripts preserve identifiers, paths, commands, and other structured tokens needed by downstream software. It contains 300 human-recorded English workplace segments (5.59 hours, 85 speakers) and 1,482 audited entities across 26 types and eight domains. Under a raw-audio-only protocol, we evaluate 19 batch and streaming systems using WER, Canonical Token/Entity Match (CTEM), and strict segment-level Task Success Rate (TSR). Across systems, WER has little rank agreement with CTEM (Spearman ρ=-0.28) or TSR (ρ=-0.22). The best CTEM and TSR are 91.8% and 68.7%. Even the strongest system therefore leaves nearly one-third of recordings with an unrecovered critical value. Symbol-, separator-, and boundary-sensitive entities account for most errors.