A speech language model trained only on audiobooks with explicit word-level prosody tokens displays emerging abilities in prosody-controlled generation, emphasis and emotion understanding, and prosodic consistency across dialogue.
Giveness, contrasitiveness, definiteness, subjects, topics, and point of view
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models
A speech language model trained only on audiobooks with explicit word-level prosody tokens displays emerging abilities in prosody-controlled generation, emphasis and emotion understanding, and prosodic consistency across dialogue.