Data-Driven Modeling of the Spatial Sound Experience
Data-Driven Modeling of the Spatial Sound Experience
复制标题
空间声音体验的数据驱动建模
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
A. Kohlrausch
中科院分区：
文献类型：
--
作者：
Aki Härmä;Munhum Park;A. Kohlrausch
由于音频系统或处理方案的评估是耗时和资源昂贵的，替代的客观评估方法吸引了相当大的研究兴趣。然而，目前的感知模型还不能取代人类听众，特别是当测试刺激是复杂的，例如，一个声音场景组成的时变多个声学图像。本文描述了一种数据驱动的方法来开发一个模型来预测复杂声学场景的主观评价，其中最新的MPEG-H 3D音频倡议中收集的大量听力测试结果被用作训练数据。结果表明，几个选定的输出的各种听觉模型可能是一个有用的功能，其中线性回归和多层感知器模型合理地预测听力测试成绩的总体分布，估计均值和方差。
Since the evaluation of audio systems or processing schemes is time-consuming and resource-expensive, alternative objective evaluation methods attracted considerable research interests. However, current perceptual models are not yet capable of replacing a human listener especially when the test stimulus is complex, for example, a sound scene consisting of time-varying multiple acoustic images. This paper describes a data-driven approach to develop a model to predict the subjective evaluation of complex acoustic scenes, where the extensive set of listening test results collected in the latest MPEG-H 3D audio initiative was used as training data. The results showed that a few selected outputs of various auditory models may be a useful set of features, where linear regression and multilayer perceptron models reasonably predicted the overall distribution of listening test scores, estimating both mean and variance.