Fact · Transcription
Many ASR systems discard or generalize hesitations, which loses acoustic detail that verbatim transcription depends on.
Checked against its source on October 17, 2026
In the source's own words
“many ASR systems discard or generalize hesitations, losing important acoustic details”
Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription Systems, Jhen-Ke Lin et al., arXiv (SLaTE 2025 workshop), 2025, Abstract.
Open the original- What it measures
- The authors set this out as the reason verbatim transcription of learner speech needs labels for hesitations.
- What it does not show
- A motivation stated in the paper. It describes ASR systems in general without naming which ones.