Whisper-style speech encoders show semantic cross-lingual alignment beyond phonetics in final layers, and early-exiting boosts ASR performance on low-resource languages.
Cross-Lingual Speech Retrieval To quantify cross-lingual alignment in the encoder of Whisper- style models, we follow prior work in employing translation retrieval as a proxy task
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Languages in Whisper-Style Speech Encoders Align Both Phonetically and Semantically
Whisper-style speech encoders show semantic cross-lingual alignment beyond phonetics in final layers, and early-exiting boosts ASR performance on low-resource languages.