Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models
cs.SD
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/apoorvumang/prompt-lookup-decoding
Terminology
Sources
- Realtime-Venus: A full-duplex interaction system with asynchronous delegation
- Spoken Language Models that Think Aloud
- Accelerating Large Language Model Decoding with Speculative Sampling
- Moshi: a speech-text foundation model for real-time dialogue
- PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
- Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems