Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics

Thibault Bañeras Roux, Jane Wottawa, Mickael Rouvier, Teva Merlin +1 more

Published

Apr 30, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

May 5, 2026

Open arXiv Open DOI Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics General Pairwise Preference

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluating speech transcripts. Several studies have shown that this measure is too limited to correctly evaluate an ASR system, which has led to the proposal of other variants of metrics (weighted WER, BERTscore, semantic distance, etc.). However, they remain system-oriented, even when transcripts are intended for humans. In this paper, we firstly present Human Assessed Transcription Side-by-side (HATS), an original French manually annotated data set in terms of human perception of transcription errors produced by various ASR systems. 143 humans were asked to choose the best automatic transcription out of two hypotheses. We investigated the relationship between human preferences and various ASR evaluation metrics, including lexical and embedding-based ones, the latter being those that correlate supposedly the most with human perception.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference

Directly usable for protocol triage.

"Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal."

Reported Metrics

strong

Error rate, Wer, Bertscore, Jailbreak success rate

Useful for evaluation criteria comparison.

"In this context, the word error rate (WER) metric is the reference for evaluating speech transcripts."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

error ratewerbertscorejailbreak success rate
Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal.
  • In this context, the word error rate (WER) metric is the reference for evaluating speech transcripts.
  • Several studies have shown that this measure is too limited to correctly evaluate an ASR system, which has led to the proposal of other variants of metrics (weighted WER, BERTscore, semantic distance, etc.).

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • However, they remain system-oriented, even when transcripts are intended for humans.
  • In this paper, we firstly present Human Assessed Transcription Side-by-side (HATS), an original French manually annotated data set in terms of human perception of transcription errors produced by various ASR systems.
  • 143 humans were asked to choose the best automatic transcription out of two hypotheses.

Why it matters for eval

  • However, they remain system-oriented, even when transcripts are intended for humans.
  • In this paper, we firstly present Human Assessed Transcription Side-by-side (HATS), an original French manually annotated data set in terms of human perception of transcription errors produced by various ASR systems.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: error rate, wer, bertscore, jailbreak success rate