One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition

arXiv:2610.34623 · cs.AI, cs.CL, cs.CV, cs.LG, cs.NE · Submitted 2026-10-25 · Read on arXiv

cs.AI, cs.CL, cs.CV, cs.LG, cs.NE

Submitted: 2026-10-25

Updated: 2026-10-25

Related papers