English(EN) DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching

新的DUPAR框架提高了语音助手的检索速度和准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-16 02:42

研究人员开发了DUPAR，一个新颖的对话检索框架，旨在提高语音助手的速度和准确性。该系统采用双路径方法：一条快速路径使用适配的音频编码器搜索跨轮证据缓存，另一条较慢的路径在缓存置信度低时执行全索引检索。该框架旨在减少延迟并减轻传统自动语音识别（ASR）系统引入的错误。 AI

影响该框架可以显著提高基于语音的AI系统的性能和用户体验。

排序理由这是一篇详细介绍新信息检索框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新信息检索框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 6 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Rong Shen · 2026-09-16 02:42

DUPAR：通过带跨轮证据缓存的语音检索器实现双路径对话检索

Voice assistants grounded in external knowledge typically use automatic speech recognition (ASR) to transcribe speech queries before retrieving evidence from textual knowledge bases. This cascade adds latency and propagates recognition errors, whereas direct speech retrieval is v…