发表机构
National Taiwan University; NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE)（台湾大学; 台湾大学人工智能卓越研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有语音检索系统无法适配多样用户意图的问题，构建首个指令感知语音检索基准INSPIRE，评估四类检索范式，发现当前无方法能稳健处理所有检索意图，凸显统一架构的必要性。
AI 中文摘要
现有语音检索系统依赖固定的相似度匹配，无法适配多样的用户意图。我们推出首个指令感知语音检索基准INSPIRE，其中自然语言指令可动态指定相关性标准，包括语义内容、说话人身份、说话风格、环境声音及其组合。我们评估了四种检索范式：大型音频-语言模型、级联流水线、自监督语音模型、对比音频-语言模型。结果显示，当前没有任何方法能稳健处理所有检索意图：基于文本的方法在语义检索上表现相对较好，但在副语言属性上存在困难；而基于语音的模型在捕捉声学特性方面表现稍好，但在遵循指令时表现不佳。这些发现凸显了对具备指令感知语音检索能力的统一架构的需求。
英文摘要
Existing speech retrieval systems rely on fixed similarity matching and cannot adapt to diverse user intents. We introduce INSPIRE, the first benchmark for instruction-aware speech retrieval, in which natural-language instructions dynamically specify relevance criteria, including semantic content, speaker identity, speaking style, environmental sounds, and their combinations. We evaluate four retrieval paradigms: large audio-language models, cascaded pipelines, self-supervised speech models, and contrastive audio-language models. Our results reveal that no current method robustly handles all retrieval intents. Text-based approaches perform relatively better at semantic retrieval but struggle with paralinguistic attributes, while speech-based models are moderately better at capturing acoustic properties but falter at following instructions. These findings highlight the need for unified architectures capable of instruction-aware speech retrieval.
CommentsInterspeech 2026 long paper
