Quantization of SSL speech representations prioritizes segmental phonetics over suprasegmental lexical tone, reducing reliability for tone languages.
SpeechGLUE: How well can Self-Supervised Speech Models capture linguistic knowl- edge?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor\`ub\'a
Quantization of SSL speech representations prioritizes segmental phonetics over suprasegmental lexical tone, reducing reliability for tone languages.