JEV-VAD: Efficient Semantic Endpointing via Task-First Conditioning and Decoder-Prefix Pruning
eess.AS
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/livekit/eot-bench
Terminology
Sources
- Qwen-Audio-Jev: A Unified Interface for Audio Decisions
- Qwen2-Audio Technical Report
- Moshi: a speech-text foundation model for real-time dialogue
- Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
- Qwen3-ASR Technical Report
- Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction
- SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation
Related papers
- WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
- From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model
- Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
- pyFDN: A Python Toolbox for Feedback Delay Network Design, Analysis, and Optimization
- GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
- DM-ASR: Diarization-aware Multi-speaker ASR with Unified Offline and Online Decoding with Large Language Models