SpokenUS：一种面向任务的对话用户模拟器
SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue
AI总结：
本文提出SpokenUS，一种基于任务导向对话的语音用户模拟器，通过引入四种语音用户行为，提升了对话系统的鲁棒性与实用性。
摘要：
鲁棒的任务导向语音对话代理需要接触人们通过语音交互的全部多样性。构建能够解决这一问题的语音用户模拟器需要大规模的语音任务导向对话（TOD）数据，涵盖语音用户行为。现有数据集在规模和领域覆盖上有限，缺乏系统化的增强流程。为此，我们引入SpokenTOD，包含52,390个对话和1,034小时语音的TOD数据集，通过四种语音用户行为——跨轮次槽位、插话、不流畅和情感语调——在多样化的说话者和领域中进行增强。基于SpokenTOD，我们提出SpokenUS，一种基于TOD的语音用户模拟器，具有专门的插话架构。SpokenUS在目标覆盖方面与显著更大的模型相当，同时在人类MOS评分上大幅超越所有基线。进一步分析证实，SpokenUS的语音行为对下游代理构成有意义的挑战，使其成为训练和评估更鲁棒语音对话系统的重要实用工具。
英文摘要：
Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is prohibitively expensive. Building spoken user simulators that address this requires large-scale spoken task-oriented dialogue (TOD) data encompassing spoken user behaviors, yet existing datasets are limited in scale and domain coverage, with no systematic pipeline for augmenting them. To address this, we introduce SpokenTOD, a spoken TOD dataset of 52,390 dialogues and 1,034 hours of speech augmented with four spoken user behaviors---cross-turn slots, barge-in, disfluency, and emotional prosody---across diverse speakers and domains. Building on SpokenTOD, we present SpokenUS, a spoken user simulator grounded in TOD that decides when to speak through a dedicated turn-taking head. SpokenUS achieves comparable goal coverage to much larger models while substantially outperforming all baselines in human MOS, disclosing slot values gradually across the dialogue as humans do rather than front-loading them. Further analysis confirms that SpokenUS's spoken behaviors pose meaningful challenges to voice agents, making it a practical tool for evaluating more robust spoken dialogue systems. Our code is available at https://github.com/holi-lab/SpokenUS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
