LLM Digest

Story

arxiv_cs_lg · Nov 1, 2026 · paper

Source brief

ReFrame: Silence-Aware Compute Reclamation for Full-Duplex Speech Models

arxiv.orgNov 1, 2026
original source linked

In brief

Full-duplex speech models execute dense model inference for every audio frame throughout a live interaction. This uniform framewise schedule creates sustained GPU load across dialogue states whose computation has strong, reusable temporal structure. ReFrame formulates full-duplex

Read the original at arxiv.org →Open in live feed Read that day’s brief

ReFrame: Silence-Aware Compute Reclamation for Full-Duplex Speech Models

Earlier in this thread 4 items

From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition

Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms

Streaming Speech Recognition on a Microcontroller: a 65.7M-Parameter Transducer in 2 and 4 Bits on the ESP32-P4

Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI