MOPSA uses K-means clustered speaker prompts with a trained router to provide zero-shot, real-time Whisper adaptation for elderly speech, achieving WER/CER reductions on DementiaBank Pitt and JCCOCC MoCA.
Cluster-based prompt-experts and dynamic router networks allow zero-shot, real-time adaptation to unseen speak- ers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
MOPSA uses K-means clustered speaker prompts with a trained router to provide zero-shot, real-time Whisper adaptation for elderly speech, achieving WER/CER reductions on DementiaBank Pitt and JCCOCC MoCA.