How to Reduce Whisper Hallucination

arXiv:2609.32560 · cs.CL · Submitted 2026-09-26 · Read on arXiv

cs.CL

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/malaysia-ai/dataset

Terminology

• Hallucination — 40× in this paper · explained in 4 episodes
• Benchmark — 16× in this paper · explained in 2 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Pseudo-labels — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Aphasia — 2× in this paper · explained in 1 episode
• alpha — 2× in this paper · explained in 1 episode
• Ablation — 1× in this paper · explained in 1 episode
• Accountability — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes

Sources

• Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
• FMA: A Dataset For Music Analysis
• FSD50K: An Open Dataset of Human-Labeled Sound Events
• The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
• Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
• Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
• LoRA: Low-Rank Adaptation of Large Language Models
• Careless Whisper: Speech-to-Text Hallucination Harms
• Granary: Speech Recognition and Translation Dataset in 25 European Languages
• Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
• Earnings-22: A Practical Benchmark for Accents in the Wild
• SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
• VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering