paper-with-me

홈 › Papers

From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection

2026-06-22 · Jan Jasiński, Mateusz Barański, Julitta Bartolewska, Marcin Witkowski, Konrad Kowalczyk arxiv

Hallucinations of ASR models - fluent transcriptions with no basis in audio - degrade system performance and pose risks in downstream applications. Robust detection of such errors remains a challenge. This paper studies Whisper large v3 hallucination detection on real-speech human-annotated data across three paradigms: text-based, LLM-based, and internal decoder state probing. Text classifiers utilizing metrics for text evaluation achieve high recall but degrade without reference transcripts. LLM-based detection improves precision with domain-specific prompt conditioning, yet remains less competitive than the lightweight text-based methods. Probing Whisper's decoder representations, without a ground-truth reference, yields the strongest performance, revealing that hallucination traits are encoded across intermediate decoding layers. A late-fusion meta-classifier combining text and internal-state outputs achieves the best overall detection performance.

📄 PDF Abstract BibTeX arXiv:2606.23060

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Careless Whisper: Speech-to-Text Hallucination Harms

2024-02-12 · Allison Koenecke, Anna Seo Gyeong Choi, Katelyn X. Mei, Hilke Schellmann 외

Speech-to-text services aim to transcribe input audio as accurately as possible. They increasingly play a role in everyday life, for example in personal voice assistants or in customer-company interactions. We evaluate O…

HallucinationLanguage ModelingLanguage Modellingspeech-recognition+2

Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio

2025-01-20 · Mateusz Barański, Jan Jasiński, Julitta Bartolewska, Stanisław Kacprzak 외

Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced by non-speech audio segments present du…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down

2025-05-19 · Yingzhi Wang, Anas Alhmoud, Saad Alsahly, Muhammad Alqurishi 외

OpenAI's Whisper has achieved significant success in Automatic Speech Recognition. However, it has consistently been found to exhibit hallucination issues, particularly in non-speech segments, which limits its broader ap…

Automatic Speech RecognitionDecoderHallucinationspeech-recognition+1

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

2026-06-05 · Georgii Aparin, Vadim Popov, Tasnima Sadekova, Assel Yermekova arxiv

Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input. We investigate whether hallucinations can be dete…

A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models

2024-09-16 · Ryandhimas E. Zezario, Sabato M. Siniscalchi, Hsin-Min Wang, Yu Tsao

This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which use…

Automatic Speech RecognitionPrompt Engineeringspeech-recognitionSpeech Recognition