Environmental Sound Recognition with Classical Machine Learning Algorithms

被引：1

作者：

Jekic, Nikolina ^{[1
]}

Pester, Andreas ^{[1
]}

机构：

[1] Carinthia Univ Appl Sci, Villach, Austria

来源：

SMART INDUSTRY & SMART EDUCATION | 2019年 / 47卷

关键词：

Machine learning; ESR; !text type='Python']Python[!/text; Audio feature extraction MFFC; k-Nearest Neighbors; Logistic regression; Support Vector Machines;

D O I：

10.1007/978-3-319-95678-7_2

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The field of study interested in the development of computer algorithm for transforming data into intelligent actions is known as machine learning. The paper investigates different machine learning classification algorithms and their effectiveness in environmental sound recognition. Efforts are made in selecting the suitable audio feature extraction technique and finding a direct connection between audio feature extraction technique and the quality of the algorithm performance. These techniques are compared to determine the most suitable for solving the problem of environmental sound recognition.

引用

页码：14 / 21

页数：8

共 12 条

[1]

[Anonymous], 2004, Tech. Rep.

[2]

[Anonymous], 2015, MACHINE LEARNING R L

[3]

Bountourakis V, 2015, MACHINE LEARNING ALG

[4]

Chu S., 2009, IEEE T AUDIO SPEECH

[5]

Coelho L.P., 2015, Building_machine_learning_systems_with_Python

[6]

Cowling M, 2003, COMP TECHNIQUES ENV

[7]

Dufaux A., 2001, DETECTION RECOGNITIO

[8]

Harrington P., 2012, Machine Learning in Action

[9]

Jiang D-N., 2002, Music type classification by spectral contrast feature

[10]

Pillos A, 2016, DETECTION CLASSIFICA

← 1 2 →