Preprint
WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper
Emmanuel Akinrintoyo et al., arXiv, 2025
Read the originalRead on October 17, 2026
- What it is
- A 2025 study of Whisper on dementia speech, which is full of pauses, repetitions and fillers. The authors report that Whisper tends to drop filler words and that this causes errors in the words next to them.
- How much weight it carries
- Preprint, not yet peer-reviewed, on one clinical speech population. The filler-omission point is a side observation rather than the paper's main measurement, so treat it as a qualitative finding.
Facts taken from this source
- A 2025 study on dementia speech says that Whisper tends to omit filler words such as uh and um from its transcripts.
“Whisper tends to omit filler words such as uh and um in its transcriptions” (Discussion)
Pages that rest on this source
- AI Dictation: How AI Voice Typing WorksGuide
- Is Speech to Text AI? What Kind of AI Voice Typing UsesGuide
- AI Cleanup for Dictation: Fillers, Punctuation, RewritesGuide
- Speech to Text for AI: Why Spoken Prompts Work BetterGuide
- Speech to Text Without AI: Dictation With No AI RewriteGuide
- Verbatim vs Clean Verbatim TranscriptionGuide
- How do you transcribe audio with timestamps for free?Question
- How do you turn off AI rewriting in a dictation app?Question
- How do you turn voice notes into text with AI?Question
- How does AI remove filler words from dictation?Question
- Is Apple Dictation better than Whisper on a Mac?Question
- Is speech to text generative AI?Question
- What is the difference between speech to text and AI?Question
- What is transcription QA, and how do you proofread a transcript?Question