Using automated syllable counting to detect missing information in speech transcripts from clinical settings

•There are significant problems with ‘off the shelf’ automatic speech transcription systems in real world settings such that they can misrepresent what and how much was actually spoken.•An automated syllable counter can more accurately represent the true number of words spoken in real world settings, and the proportion of missing syllables in transcripts strongly correlates with the automatic speech recognition word error rate.•With low quality recordings and challenging speaker characteristics the missing syllables can be used to estimate the quality of transcripts derived with automatic speech recognition systems.•This solution can be easily implemented as an automated fail-safe method. Speech rate and quantity reflect clinical state; thus automated transcription holds potential clinical applications. We describe two datasets where recording quality and speaker characteristics affected transcription accuracy. Transcripts of low-quality recordings omitted significant portions of speech. An automated syllable counter estimated actual speech output and quantified the amount of missing information. The efficacy of this method differed by audio quality: the correlation between missing syllables and word error rate was only significant when quality was low. Automatically counting syllables could be useful to measure and flag transcription omissions in clinical contexts where speaker characteristics and recording quality are problematic.