2019
DOI: 10.1121/1.5133944
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning in acoustics: Theory and applications

Abstract: Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science. We survey the recent advances and transformative potential of machine learning (ML), including deep learning, in the field of acoustics. ML is a broad family of statistical techniques for automatically detecting and utilizing patterns in data. Relative to conventional acoustics and signal processing, ML is data-driven. Given sufficient training data, ML can discover complex re… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
166
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 425 publications
(166 citation statements)
references
References 270 publications
(310 reference statements)
0
166
0
Order By: Relevance
“…Another significant contribution of this article is to inspire people to rethink noise management for CI systems. Researchers should consider the assumptions about directionality and complex non-linear patterns that can be computationally modeled by signal processing or machine learning (e.g., Bianco et al, 2019;Gong et al, 2019). Previous studies and present work provide considerable support for optimizing and updating noisesuppression techniques to improve speech-in-noise recognition for CI users.…”
Section: Discussionmentioning
confidence: 81%
“…Another significant contribution of this article is to inspire people to rethink noise management for CI systems. Researchers should consider the assumptions about directionality and complex non-linear patterns that can be computationally modeled by signal processing or machine learning (e.g., Bianco et al, 2019;Gong et al, 2019). Previous studies and present work provide considerable support for optimizing and updating noisesuppression techniques to improve speech-in-noise recognition for CI users.…”
Section: Discussionmentioning
confidence: 81%
“…With the development of deep learning (DL), researchers have begun to use DL methods to address underwater acoustic problems, such as source localization [1][2][3][4][5][6] and target detection [7]. DL can achieve specific functions by fitting training data.…”
Section: Introduction Sectionmentioning
confidence: 99%
“…Training data are obtained by either experiments or simulations. In previous DL-related work [3][4][5][6], only range-independent ocean waveguides were considered during simulations, which is far from the real ocean waveguides in many cases.…”
Section: Introduction Sectionmentioning
confidence: 99%
“…For comparison, Table 6.2 tabulates two additional 10-fold cross-validation confusion matrices using the PCA with naïve Bayes (NB) classifier and a neural network (NN) classifier with two hidden layers, with both being other methods for acoustic classification [104]. From this comparison, the proposed PCA with SVM has a better 10-fold cross-validation performance (89.4%) than the PCA with the NN (85.6%) and…”
Section: Feature Extraction and Classificationmentioning
confidence: 99%
“…It may prove interesting to explore the classification performances obtained by learning [114] or using other wellknown acoustic features. Specifically, the Mel-frequency cepstral, non-negative matrix factorization, and feature-engineering techniques [104], [115] may advance leak classification in well integrity evaluation.…”
Section: Future Workmentioning
confidence: 99%