An Evaluation of Data Augmentation Methods for Sound Scene Geotagging

Bear, Helen L.; Morfi, Veronica; Benetos, Emmanouil

doi:10.21437/interspeech.2021-1837

Cited by 4 publications

(3 citation statements)

References 9 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimizing the parameters used for data augmentation and the transforms involved within is one such proposal. Most likely, as backed up by the exposure gained through this project, it would be beneficial to try grid search for this task [5], [6].…”

Section: Discussionmentioning

confidence: 99%

Acoustic scene classification using auditory datasets

Kumpawat¹,

Dey²

2021

Preprint

View full text Add to dashboard Cite

The approach of using audio datasets to solve the problems revolving around land use patterns has gained decent amount of research exposure in the recent times. Although being a blooming domain in the field of Artificial Intelligence and Data Analysis, it would not be wrong to declare that a significant amount of journey is yet to be covered. In this paper, the project conducted to classify some pre-defined acoustic scene is discussed and explained.For the system designed INPUT : ambient audio recording of a certain scene OUTPUT : class to which the scene belongs The approach used not only challenges some of the fundamental mathematical techniques used so far in early experiments of the same trend, but also it introduces new scopes and new horizons for interesting results. The physics governing spectrograms has been optimized in the project along with exploring how it handles the intense requirements of the problem in hand. Major contributions and developments brought under the light, through this project involve using better mathematical techniques and problem specific machine learning methods.Improvised data analysis and data augmentation for audio datasets like frequency masking and random frequency-time stretching are used in the project and hence are explained in this paper. In the used methodology, audio transforms principle were also tried and explored, and indeed the insights gained were used constructively in the later stages of project. Using a deep learning principle is surely one of them.Also, in this paper the potential scopes and upcoming research openings in both short and long term tunnel of time has been presented. Although much of the results gained are domain specific as of now, but they are surely potent enough to produce novel solutions in various different domains of diverse backgrounds.

show abstract

Section: Discussionmentioning

confidence: 99%

Acoustic scene classification using auditory datasets

Kumpawat¹,

Dey²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…3. Dropout : Short time segments from the audio sample are randomly replaced with 0 values (Bear et al., 2021).…”

Section: Methodsmentioning

confidence: 99%

“…4. Stretch : Time streching is applied to the samples by resizing a random number of columns at a random position and then by resizing the image using a bilinear interpolation (Bear et al., 2021).…”

Section: Methodsmentioning

confidence: 99%

ECOGEN: Bird sounds generation using deep learning

Guei,

Christin,

Lecomte

et al. 2023

Methods Ecol Evol

View full text Add to dashboard Cite

Large‐scale acoustic projects generate vast amounts of data that can now be efficiently processed using deep learning tools. However, these tools often face limitations due to sound labeling and imbalanced sampling. Data augmentation can help overcome such challenges, particularly through the generation of synthetic and lifelike sounds. Synthetic samples can be valuable not only for deep learning but also for species with limited available data. Despite advancements in computer power, sound generation remains a time‐consuming process, even requiring a substantial number of samples. We present ECOGEN, a novel deep learning approach designed to generate realistic bird songs for biologists and ecologists. The primary objective of ECOGEN is to enhance the number of samples in under‐represented bird song classes, thereby improving the performance and robustness of classifiers in ecological research.The ECOGEN framework employs spectrograms as a representation of bird songs and leverages proven image generation techniques to create new spectrograms, subsequently converted back to digital audio signals. As a class‐agnostic tool, ECOGEN is applicable to a wide range of biophonic sounds, including mammal and insect calls. We show that adding samples generated by ECOGEN to a bird song classifier improved the classification accuracy by 12% on average and improved results compared with classic data augmentation techniques 80% of the time. Our approach is both fast and efficient, enabling the generation of synthetic bird songs on standard computing resources. By facilitating the creation of synthetic bird songs, ECOGEN can contribute to the conservation of endangered bird species, while providing valuable insights into their vocalizations, behaviours and habitat preferences. Future development of ECOGEN can be easily implemented and could focus on incorporating additional configurable parameters during the generation phase for increased control over the output, catering to the specific needs of biologists.

show abstract

Evaluating the Potential and Realized Impact of Data Augmentations

Heise,

Bear

2023

2023 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

An Evaluation of Data Augmentation Methods for Sound Scene Geotagging

Cited by 4 publications

References 9 publications

Acoustic scene classification using auditory datasets

Acoustic scene classification using auditory datasets

ECOGEN: Bird sounds generation using deep learning

Evaluating the Potential and Realized Impact of Data Augmentations

Contact Info

Product

Resources

About