Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms
arXiv:2610.38016v1 Announce Type: new Abstract: Automatic speech recognition (ASR) increasingly supplies transcripts for educational NLP, but aggregate word error rate (WER) can conceal errors concentrated in learner speech, multilingual turns, and speaker attribution. We compare platform-integrated
Der Artikeltext wird beim nächsten Sync nachgeladen. Original bei arXiv cs.CL lesen
Quelle: arXiv cs.CL (arXiv cs.CL). Original öffnen