arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.09708cs.ROcs.AIstat.CO
收藏

不再含糊:通过语音适配提升机器人语音可懂度

No More Mumbles: Enhancing Robot Intelligibility through Speech Adaptation

Ghent University(根特大学);imec;Faculty of Engineering and Architecture(工程与建筑学院)

Qiaoqiao Ren, Yuanbo Hou, Dick Botteldooren, Tony Belpaeme

AI总结:

针对机器人固定语音参数影响用户理解的问题,研究通过语音理解实验明确环境因素的影响,构建预测模型与卷积神经网络实现语音自适应,验证了其在可懂度和用户体验上的优势。

摘要:

口语交互是人际沟通的核心,人们会灵活调整自身语音以适配不同对象与环境。令人意外的是,机器人以及其他数字设备并未配备语音适配能力,反而依赖固定的语音参数,这往往会阻碍用户的理解。我们开展了一项语音理解研究,共招募39名参与者,让他们处于不同的环境与情境条件下。实验过程中,机器人采用不同的发声参数念出单词,参与者需要完成两项任务:识别听到的单词,以及对机器人语音的主观印象打分。实验主要结果显示,声学质量良好的空间与语音可懂度、用户体验呈正相关。然而,用户与机器人之间距离的增加会降低用户体验,而干扰性背景音会显著降低语音识别准确率与用户满意度。随后我们为机器人构建了自适应语音系统。要实现这一点,机器人需要知晓用户在特定环境下理解口语的难度。我们提出了一种预测模型,用于评估环境声学环境的干扰程度,进而评估在此环境下理解他人话语的难度。接着,我们开发了一个卷积神经网络(convolutional neural network)模型,用于让机器人的语音参数适配不同用户与空间,同时考虑环境声学对可懂度的影响。最后,我们通过27名用户开展了评估,结果表明,与固定语音相比,采用自适应语音参数的机器人在可懂度和用户体验上表现更优。

英文摘要:

Spoken language interaction is at the heart of interpersonal communication, and people flexibly adapt their speech to different individuals and environments. It is surprising that robots, and by extension other digital devices, are not equipped to adapt their speech and instead rely on fixed speech parameters, which often hinder comprehension by the user. We conducted a speech comprehension study involving 39 participants who were exposed to different environmental and contextual conditions. During the experiment, the robot articulated words using different vocal parameters, and the participants were tasked with both recognising the spoken words and rating their subjective impression of the robot's speech. The experiment's primary outcome shows that spaces with good acoustic quality positively correlate with intelligibility and user experience. However, increasing the distance between the user and the robot exacerbated the user experience, while distracting background sounds significantly reduced speech recognition accuracy and user satisfaction. We next built an adaptive voice for the robot. For this, the robot needs to know how difficult it is for a user to understand spoken language in a particular setting. We present a prediction model that rates how annoying the ambient acoustic environment is and, consequentially, how hard it is to understand someone in this setting. Then, we develop a convolutional neural network model to adapt the robot's speech parameters to different users and spaces, while taking into account the influence of ambient acoustics on intelligibility. Finally, we present an evaluation with 27 users, demonstrating superior intelligibility and user experience with adaptive voice parameters compared to fixed voice.

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。

↑