Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
14
datasets available to search
ShareScore release 0.9.0
Dataset results
14 results for “sound recognition”
Data from: Domain-specific neural networks improve automated bird sound recognition already with small amount of local data
<p><span><span>An automatic bird sound recognition system is a useful tool for collecting data of different bird species for ecological analysis. Together with autonomous recording units (ARUs), such a system provides a possibility to collect bird observations on a scale that no human observer could ever match. During the last decades progress has been made in the field of automatic bird sound recognition, but recognizing bird species from untargeted soundscape recordings remains a challenge. <br></span></span></p> <p><span><span>In this article we demonstrate the workflow for building a global identification model and adjusting it to perform well on the data of autonomous recorders from a specific region. We show how data augmentation and a combination of global and local data can be used to train a convolutional neural network to classify vocalizations of 101 bird species. We construct a model and train it with a global data set to obtain a base model. The base model is then fine-tuned with local data from Southern Finland in order to adapt it to the sound environment of a specific location and tested with two data sets: one originating from the same Southern Finnish region and another originating from a different region in German Alps.<br></span></span></p> <p><span><span>Our results suggest that fine-tuning with local data significantly improves the network performance. Classification accuracy was improved for test recordings from the same area as the local training data (Southern Finland) but not for recordings from a different region (German Alps). Data augmentation enables training with a limited number of training data and even with few local data samples significant improvement over the base model can be achieved. Our model outperforms the current state-of-the-art tool for automatic bird sound classification.<br></span></span></p> <p><span><span>Using local data to adjust the recognition model for the target domain leads to improvement over general non-tailored solutions. The process introduced in this article can be applied to build a fine-tuned bird sound classification model for a specific environment.</span></span></p>
Data from: Domain-specific neural networks improve automated bird sound recognition already with small amount of local data
Open the record for dataset details and reuse information.
Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts Data and Scripts
<p>The repository contains the data corresponding to the Paper "Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts".</p> <p>Random30, Random50, Random100, Similiar10, Similar30 and Similar50.zip contain the data sets (obj Files).</p> <p>R30_physical_images.zip and sim50_physical_images.zip contain the photos made from the physical components which are used for the evaluation.</p>
Vanellus chilensis dataset accompanying PLOS ONE paper "Automated Sound Recognition Provides Insights into the Behavioral Ecology of a Tropical Bird"
<p>Southern Lapwing <em>Vanellus chilensis</em> dataset accompanying the PLOS ONE article</p> <p>O. Jahn, T. Ganchev, M.I. Marinez and K.L. Schuchmann: Automated Sound Recognition Provides Insights into the Behavioral Ecology of a Tropical Bird. DOI:10.1371/journal.pone.0169041</p> <p>---<br> BL01:<br> Background Library 01 consists of</p> <p>BL01 >> BL_CHVACH_free_final:<br> 54 hand-cleaned (<em>Vanellus chilensis</em>-free) background files and</p> <p>BL01 >> PSC008_forest:<br> 36 original soundscapes recorded inside forest, which may contain a few target signals from overflying lapwings.</p> <p>---<br> PONE_VACH_AnnualCycle_Statistics:<br> Contains the Excel files<br> - 2013CHVACH_BreedingCycle_Statistics_PONE: statistics on <em>V. chilensis</em> activity patterns, Apr. 2013 to Sep. 2013.<br> - 2013CHVACH_FalseNegatives_PONE: determination of the false negative rate based on an expert-annotated sample of 26 soundcsape recordings<br> - 2013CHVACH_FalsePositives_PONE: determination of the false positive rate based on an expert-annotated random sample of 1250 automated <em>V. chilensis</em> detections.</p> <p>---<br> TL01_BIAVCHCHVACH_20130813v2_HandCleaned:<br> Training library for the development of the <em>V. chilensis</em> recognizer, consisting of 90 hand-filtered recordings of the target species.</p> <p>---<br> VACH_Detector_results >> VACHdetectorOutput_PONE.zip:<br> TXT detector output files, listing timestamps of potential <em>V. chilensis</em> sound events.</p> <p>---<br> VACH_FNrate_20160706:<br> Validation library used to determine the false negative rate. The library consists of 26 expert-annotated sound files. Annotations were made in Adobe Audion v3.0.</p> <p>---<br> VL01_VACH_MonoB<br> and<br> VL01_VACH_MonoB:<br> Validation library used for the fine-tuning of the recognizer settings.</p> <p>---<br> Important notes on the annotation of the VACH_FNrate_20160706 library:</p> <p>1) In general, we used the procedure described in Ganchev et al. 2015 for the annotation of VACH validation libraries (see next section).</p> <p>2) However, the detector-generated timestamps were not changed! For the following reasons, it is not possible to use the VACH_FN_rate library as a validation library for the development of improved recognizer versions:</p> <p>(a) The VACH detector overlooked many of the weaker signals within a VACH call series. Therfore the detector-generated annotations are incomplete.<br> (b) For the same reason some automatically-generated detections may refer to a single VACH call event (double hits).</p> <p>Details on the method used for the annotation of the VACH validation libraries are described in Ganchev et al. 2015, pp.6100f: 2.1.3.3.Vanellus chilensis validation dataset.</p>
A Comprehensive Central Kurdish Sound Dataset for Robust Automatic Speech Recognition (Part 1).
<p>Exploring the intricacies of Speech Recognition Technology (SRT), our dataset encompasses a wide range of age demographics, spanning from adolescents to individuals in their fifties. This diverse dataset comprises a substantial collection of raw data, amounting to 1,739,089 entries. Within this dataset, a meticulous curation process has yielded a total of 1,683 hours of data, providing a thorough examination of language acquisition patterns across different age cohorts within the Central Kurdish linguistic domain.</p>
To bee or not to bee: An annotated dataset for beehive sound recognition
<p><strong>-- Dataset documentation --</strong></p> <p><br> <strong>1- Introduction</strong></p> <p>The present dataset was developed in the context of our work in [1] that focus on the automatic recognition of beehive sounds. The problem is posed as the classification of sound segments in two classes: Bee and noBee. The novelty of the explored approach and the need for annotated data, dictated the construction of such dataset.</p> <p><strong>2- Description</strong></p> <p><strong>2.1- Audio recordings:</strong></p> <p>The annotated dataset was developed based on a selected set of recordings acquired in the context of two different projects: the Open Source Beehive (OSBH) project [2] and the NU-Hive project [3]. Both projects main goal is to develop a beehive monitoring system capable of identifying and predict certain events and states of the hive that are of interest to the beekeeper. Among many different variables that can be measured and that help the recognition of different states of the hive, the analysis and use of the sound the bees produce is a big focus for both projects.</p> <p>The recordings from the OSBH project were acquired through a citizen science initiative which asked people from the general public to record the sound from their beehives together with the registering of the hive state at the moment. Because of the amateur and collaborative nature of this project, the recordings from the OSBH project present great diversity due to the very different conditions in which the signals were acquired: different recording devices used, different environments where the hives were placed, and even different position for the microphones inside the hive. This variety of settings makes this dataset a very interesting tool to help evaluate and challenge the methods developed.</p> <p>The NU-Hive project is a comprehensive effort of data acquisition, concerning not only sound, but a vast amount of variables that will allow the study of bees behaviors and other unknown aspects. The selected recordings are taken from 2 hives and labeled regarding two states: queen bee is present, and queen bee not present. Contrary to the OSBH project recordings, the recordings from the NU-Hive project are from a much more controlled and homogeneous environment. Here the occurring external sounds are mainly traffic, car honks and birds.</p> <p><strong>The annotated dataset:</strong></p> <p>For each selected recording, time segments are labeled as Bee or noBee depending on the perceived source of the sound signal being from bees or external to the hive.</p> <p>The whole annotated dataset consists of 78 recordings of varying lengths which make up for a total duration of approximately 12 hours of which 25% is annotated as noBee events.</p> <p>About 60% of the recordings are from the NU-Hive dataset and represent 2 hives, the remaining are recordings from the OSBH dataset and 6 different hives. The recorded hives are from 3 main locations: North America, Australia and Europe.</p> <p> </p> <p><strong>2- Annotation procedure<a href="http://localhost:8888/notebooks/Dropbox/QMUL/BEESzzzz/Data/Annotations/readme.ipynb#2--Annotation-procedure">¶</a></strong></p> <p>The annotation procedure consists in hearing the selected recordings and marking the beginning and the end of every sound that could not be recognized as a beehive sound. The recognition of external sounds is based primarily on the perceived heard sounds, but a visual aid is also used by visualizing the log-mel frequency spectrum of the signal. All the above are functionalities offered by the Sonic Visualiser software, which was used by two volunteers that are neither bee-specialists nor specially trained in sound annotation tasks.</p> <p>By marking these pairs of moments corresponding to the beginning and end of external sound periods, we are able to get the whole recording labeled into Bee and noBee intervals. Thus in the resulting Bee intervals only pure beehive sounds, (no external sounds) should be perceived for the entirety of the segment. The noBee intervals refer to periods where an external sound can be perceived (superimposed to the bee sounds).</p> <p> </p> <p><strong>File Structure:</strong></p> <p>Each audio file is coupled with its corresponding annotation file, identified by the same name and extension <em>.lab</em>.<br> For convenience, all the annotations are collected in a single master label file named <em>beeAnnotations.mlf</em></p> <p>The <em>.lab</em> files consist of : </p> <ul> <li>First row identifies the audio file to which the annotations refer to.</li> <li>Each line after that describes an interval with starting time point, end time point and label. The time points are expressed in seconds.</li> </ul> <p>Below is an example of such an annotation file: </p> <pre><code>Hive3_20_07_2017_QueenBee_H3_audio_15_30_00 0 78.45 bee 78.46 78.95 nobee 78.96 103.92 bee 103.93 112.48 nobee 112.49 152.48 bee . </code></pre> <p>This dataset is licensed under a Creative Commons Attribution 4.0 International License.<br> When using this dataset, please cite [1]:</p> <p>[1] I. Nolasco and E. Benetos, “To bee or not to bee: Investigating machine learning approaches to beehive sound recognition,” in Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), 2018, submitted.</p> <p>[2] “Open Source Beehives Project,” https://www.osbeehives.com/.</p> <p>[3] S. Cecchi, A. Terenzi, S. Orcioni, P. Riolo, S. Ruschioni, and N. Isidoro, “A preliminary study of sounds emitted by honey bees in a beehive,” in Audio Engineering Society Convention 144, 2018.</p>
Recognition of sounds by ensembles of proteinoids
<p>Proteinoids are artificial polymers that imitate certain characteristics of natural proteins, including self-organization, catalytic activity, and responsiveness to external stimuli. This paper investigates the potential of proteinoids as organic audio signal processors. We convert sounds of the English alphabet into waveforms of electrical potential, feed the waveforms into proteinoid solutions and record electrical responses of the proteinoids. We also undertake a detailed comparison of proteinoids' electrical responses (frequencies, periods, and amplitudes) with original input signals. We found that responses of proteinoids are less regular and have lower dominant frequency, wider distribution of proteinoids and less skewed distribution of amplitudes compared with input signals. We found that letters of the English alphabet uniquely map onto a pattern of electrical activity of a proteinoid ensemble, that is the proteinoid ensembles recognise spoken letters of the English alphabet. The finding will be used in further designs of organic electronic devices, based on ensembles of proteinoids, for sound processing and speech recognition.</p>
Recognition of sounds by ensembles of proteinoids
Open the record for dataset details and reuse information.
Data from: AviaNZ: a future-proofed program for annotation and recognition of animal sounds in long-time field recordings
The routine collection of long‐time acoustic recordings of animals in the field presents new challenges in data analysis. While many terabytes of data are collected annually, effective use of this noisy, highly variable data require skilled humans to manually identify calls. While computer programs to automatically analyse these recordings are becoming available, it is important that they are user‐friendly and easy‐to‐use, so that everybody – citizen scientists, wildlife managers, researchers – can take advantage of them, and that they keep the human in the loop so analyses carried out this year are comparable both to manual call counts from the past, and more accurate automated analyses performed in the future. We present the AviaNZ program, which is designed to achieve these goals: the software includes methods for simple, rapid manual annotation of recordings, denoising and segmentation methods, and a training procedure by which the user can prepare their own filters to automatically recognize individual species. The software can run in batch mode, automatically processing folders of field recordings, and then present the outputs to enable the quick and easy review of the results. Finally, the outputs are presented in a variety of spreadsheets to enable different statistical analyses to be performed. We describe the various workflows of manually and semi‐automatically processing sound files, annotating them to train automatic filters, using those filters in batch mode, and how the software facilitates rapid evaluation of the automated analysis. A demonstration of the software, comparing manual and automatic detection of calls of the little spotted kiwi Apteryx owenii is given. It shows that while the automatic detection does produce false positives, human correction of these is far faster than manual review of the whole sound file. AviaNZ is a freely available open‐source standalone program. Our experience shows that it can be used by anybody quickly and easily. However, for experienced users it is easily customizable and extendable. By enabling everybody involved with acoustic bird recording to quickly and easily analyse their own data, while future‐proofing it by keeping the human in the loop, we are enabling acoustic field recordings to meet their potential.
The Effect of Noise Pollution on Lung Sound Recognition by Medical Students
ClinicalTrials.gov study NCT05731193. IPD Sharing: NO. Countries: 1. Publications: 8.
Data from: AviaNZ: a future-proofed program for annotation and recognition of animal sounds in long-time field recordings
Open the record for dataset details and reuse information.
Cochlear Implant Speech and Non-speech Sound Recognition
ClinicalTrials.gov study NCT03661970. IPD Sharing: NO. Countries: 1. Publications: 0.
Study on AI Recognition System Of Heart Sound In Congenital Heart Disease Screening
ClinicalTrials.gov study NCT04307030. IPD Sharing: UNDECIDED. Countries: 1. Publications: 0.
Data from: Passive acoustics and sound recognition provide new insights on status and resilience of an iconic endangered marsupial (koala Phascolarctos cinereus) to timber harvesting
Open the record for dataset details and reuse information.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.