# Adopting Whisper for Confidence Estimation

arXiv: https://arxiv.org/abs/2502.13446 · HTML: https://mlsanity.com/paper/2502.13446/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [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)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency](https://mlsanity.com/paper/2003.12710/) (2020)
- [Deliberation Model Based Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/2003.07962/) (2020)
- [Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition](https://mlsanity.com/paper/2010.11428/) (2020)
- [Learning Word-Level Confidence For Subword End-to-End ASR](https://mlsanity.com/paper/2103.06716/) (2021)
- [Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1810.13025/) (2018)
- [Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction](https://mlsanity.com/paper/2104.12870/) (2021)
- [Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.03327/) (2021)
- [Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2212.08703/) (2022)

## Built on by (most cited first, 2 of 2)

- [Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels](https://mlsanity.com/paper/2509.25516/) (2025)
- [Enhancing ASR Performance in the Medical Domain for Dravidian Languages](https://mlsanity.com/paper/2604.19797/) (2026)

## Abstract (arXiv)

Recent research on word-level confidence estimation for speech recognition systems has primarily focused on lightweight models known as Confidence Estimation Modules (CEMs), which rely on hand-engineered features derived from Automatic Speech Recognition (ASR) outputs. In contrast, we propose a novel end-to-end approach that leverages the ASR model itself (Whisper) to generate word-level confidence scores. Specifically, we introduce a method in which the Whisper model is fine-tuned to produce scalar confidence scores given an audio input and its corresponding hypothesis transcript. Our experiments demonstrate that the fine-tuned Whisper-tiny model, comparable in size to a strong CEM baseline, achieves similar performance on the in-domain dataset and surpasses the CEM baseline on eight out-of-domain datasets, whereas the fine-tuned Whisper-large model consistently outperforms the CEM baseline by a substantial margin across all datasets.