Causal full-duplex speech LLMs improve response quality by recursively feeding soft vocabulary embeddings as latent thoughts during listening, trained by matching a non-causal expert posterior via ELBO.
Instruction data generation and unsu- pervised adaptation for speech language models.arXiv preprint arXiv:2406.12946, 2024a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
Causal full-duplex speech LLMs improve response quality by recursively feeding soft vocabulary embeddings as latent thoughts during listening, trained by matching a non-causal expert posterior via ELBO.