日本語のみで絞り込む
Welcome to Full-Duplex-Bench, with v1.0, v1.5, v2.0, and v3.0, a comprehensive framework designed to evaluate the conversational and turn-taking capabilities of ...
Full-Duplex-Bench Full-Duplex-Bench Public. A Benchmark for Evaluating Turn-Taking and Overlap Handling in Full-Duplex Spoken Dialogue Models. Python 350 38.
Sequences of API calls across 4 domains (Travel, Finance, Housing, E-Commerce) with deterministic outputs for automatic scoring. ⏱. Latency Decomposition. Fine ...
In this paper, we present Full-Duplex-Bench, the first scenario-driven benchmark for systematically evaluating key turn-taking behaviors in human-to-machine ...
A curated list of full-duplex spoken dialogue models & benchmarks - Ruiqi-Yan/Awesome-Full-Duplex-SDM.
FD-Bench is a comprehensive benchmarking pipeline specifically designed for evaluating Full-Duplex Spoken Dialogue Systems (FD-SDS). This benchmark provides ...
We introduce Full-Duplex-Bench-v2 (FDB-v2), a streaming framework that integrates with an automated examiner that enforces staged goals under two pacing setups ...
They introduce Full-Duplex-Bench v1.5, a modular, fully automated benchmark that simulates four overlap scenarios: user interruption, listener backchannel, side ...