扩充并分析开放音频质量数据集ODAQ，助力客观评价模型测试
Expanding and Analyzing ODAQ -- the Open Dataset of Audio Quality
- 招募学生听众训练后开展主观评测，提升数据覆盖
- 新增3个实验室、42名听者，共10080条主观评分
- 首次将ODAQ用于评估客观音质指标的预测能力
开放音频质量数据集（ODAQ）旨在解决公开可用音频数据集及其主观质量评分稀缺的问题。该数据集采用宽松许可发布，包含六种信号处理方法在五个质量等级下生成的音频，以及对应的主观测试结果。为扩展数据集，我们对大学生进行听觉训练后开展进一步主观测试，结果与先前专家听者一致。研究还分析了不同训练方式对绝对量表和锚点使用的影响。扩充后的数据集涵盖三个国际实验室的数据，共42名听者，10080条主观评分。本文详细描述了扩展过程并进行深入分析，首次将ODAQ作为基准，评估客观音频质量指标预测主观评分的能力。
原文摘要 · Abstract (English)
The Open Dataset of Audio Quality (ODAQ) was recently introduced to address the scarcity of openly available audio datasets with corresponding subjective quality scores. The dataset, released under permissive licenses, comprises audio material processed using six different signal processing methods operating at five quality levels, along with corresponding subjective test results. To expand the dataset, we provided listener training to university students to conduct further subjective tests and obtained results consistent with previous expert listeners. We also showed how different training approaches affect the use of absolute scales and anchors. The expanded dataset now comprises results from three international laboratories providing a total of 42 listeners and 10080 subjective scores. This paper provides the details of the expansion and an in-depth analysis. As part of this analysis, we initiate the use of ODAQ as a benchmark to evaluate objective audio quality metrics in their ability to predict subjective scores
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。