Perch publishes three open releases for checking drug names in dictation

Description and use

Perch released three open resources—phoneme lane, vet drug pronunciations, and blind dictation corpora—to enable reproducible testing of drug name recognition in veterinary dictation.

Problem

Existing dictation systems misrecognize veterinary drug names, making accurate transcription difficult.

Outcome

Perch’s releases provide reproducible, open resources for evaluating veterinary drug name recognition, facilitating community testing and improvement of ASR systems.

Workflow

• 1. Run phoneme lane on dictation audio to score drug names against phoneme model.
• 2. Use vet drug pronunciations table to map names to IPA for American, British, and South Asian English.
• 3. Test ASR systems against blind dictation corpora (70 rows each, 45 dictations + 25 traps).
• 4. Compare ASR outputs (Whisper large v3, MedASR) to ground truth and identify misrecognitions.
• 5. Report misses via issue on corresponding GitHub repo.

Evidence

The phoneme lane scores the audio, not the transcript.

Source

Vet drug pronunciations lists 265 drug and brand names used in veterinary practice, each with its pronunciation in IPA.

Source

Blind dictation corpora are six sets of 70 rows, each a dictation or a trap, each written by an author who never saw Perch's matching code.

Source