Grup de Recerca en Tecnologies Mèdia (GTM), La Salle-URL, c/Quatre Camins, 30, 08022 Barcelona, Spain.
Sensors (Basel). 2021 Feb 11;21(4):1274. doi: 10.3390/s21041274.
Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.
在过去的几年中,声学事件检测和分析得到了广泛的发展,因为它在监测老年人或依赖者、监控问题、多媒体检索,甚至在自然环境中的生物多样性指标方面都有很有价值的应用。为此,声源识别是为所有上述应用提供智能技术答案的关键问题。不同类型的声音和多变的环境,以及在应用方面的一些挑战,扩大了人工智能算法建议的选择范围。本文对几种特征提取算法(梅尔频率倒谱系数 (MFCC)、Gamma 频率倒谱系数 (GTCC) 和窄带 (NB))与一组机器学习算法 (-最近邻 (kNN)、神经网络 (NN) 和高斯混合模型 (GMM))进行了比较研究,在五个不同的声学环境中进行了测试。这项工作的目的是详细说明一种最佳实践方法,并评估这种通用算法对所有类别的可靠性。初步结果表明,在大多数描述的语料库中,特征提取和机器学习的大多数组合都能得到可接受的结果。然而,有一种组合优于其他组合:使用 GTCC 结合 kNN,并且对所有语料库进一步分析了其结果。