A bottom-up ASR system that recognizes articulatory attributes before assembling them into syllables matches direct syllable models on Mandarin and shows better zero-shot transfer to Japanese.
Title resolution pending
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
-
A Bottom-up Framework with Language-universal Speech Attribute Modeling for Syllable-based ASR
A bottom-up ASR system that recognizes articulatory attributes before assembling them into syllables matches direct syllable models on Mandarin and shows better zero-shot transfer to Japanese.