paper-with-me

홈 › Papers

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

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

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 application in complex industrial settings. In this paper, we introduce a novel method to reduce Whisper's hallucination on non-speech segments without using any pre- or post-possessing techniques. Specifically, we benchmark the contribution of each self-attentional head in the Whisper-large-v3 decoder to the hallucination problem by performing a head-wise mask. Our findings reveal that only 3 of the 20 heads account for over 75% of the hallucinations on the UrbanSound dataset. We then fine-tune these three crazy heads using a collection of non-speech data. The results show that our best fine-tuned model, namely Calm-Whisper, achieves over 80% reduction in non-speech hallucination with only less than 0.1% WER degradation on LibriSpeech test-clean and test-other.

📄 PDF Abstract BibTeX arXiv:2505.12969

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionDecoderHallucinationspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

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…

Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection

2026-09-03 · Maryam Abbasihafshejani, Murtuza Jadliwala arxiv

Whisper is a widely used foundation model for automatic speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts for inputs containing little or no speech. We propose a training-fr…

Speech Recognition

Listen Like a Teacher: Mitigating Whisper Hallucinations using Adaptive Layer Attention and Knowledge Distillation

2025-11-18 · Kumud Tripathi, Aditya Srinivas Menon, Aman Gaurav, Raj Prakash Gohil 외 arxiv

The Whisper model, an open-source automatic speech recognition system, is widely adopted for its strong performance across multilingual and zero-shot settings. However, it frequently suffers from hallucination errors, es…

Knowledge DistillationSpeech Recognition

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

Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding

2026-03-06 · Hoseong Ahn, Jeongyun Chae, Yoonji Park, Kyuhong Shim arxiv

Long-form speech recognition with large encoder-decoder models such as Whisper often exhibit hallucinations, repetition loops, and content omissions. These errors can accumulate and be further amplified when the previous…

Speech Recognition