code.html

<!DOCTYPE HTML>
<!--
	Phantom by HTML5 UP
	html5up.net | @ajlkn
	Free for personal and commercial use under the CCA 3.0 license (html5up.net/license)
-->
<html>

<head>
	<title>Open-source Code and Data | MagCIL</title>
	<meta name="description" content="Open-source libraries, tools and datasets released by MagCIL for audio, speech, music and multimodal machine learning, including pyAudioAnalysis, deepaudio-x and deepaudio-lab." />
	<link rel="canonical" href="https://magcil.github.io/code.html" />

	<meta property="og:type" content="website" />
	<meta property="og:site_name" content="MagCIL" />
	<meta property="og:title" content="Open-source Code and Data | MagCIL" />
	<meta property="og:description" content="Open-source libraries, tools and datasets released by MagCIL for audio, speech, music and multimodal machine learning, including pyAudioAnalysis, deepaudio-x and deepaudio-lab." />
	<meta property="og:url" content="https://magcil.github.io/code.html" />
	<meta property="og:image" content="https://magcil.github.io/images/og-image.png" />
	<meta property="og:image:width" content="1200" />
	<meta property="og:image:height" content="630" />

	<meta name="twitter:card" content="summary_large_image" />
	<meta name="twitter:title" content="Open-source Code and Data | MagCIL" />
	<meta name="twitter:description" content="Open-source libraries, tools and datasets released by MagCIL for audio, speech, music and multimodal machine learning, including pyAudioAnalysis, deepaudio-x and deepaudio-lab." />
	<meta name="twitter:image" content="https://magcil.github.io/images/og-image.png" />
	<meta charset="utf-8" />
	<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no" />
	<link rel="stylesheet" href="assets/css/main.css" />
	<noscript>
		<link rel="stylesheet" href="assets/css/noscript.css" />
	</noscript>
	<!-- Global site tag (gtag.js) - Google Analytics -->
	<script async src="https://www.googletagmanager.com/gtag/js?id=G-YFBP31Y1CZ"></script>
	<script>
		window.dataLayer = window.dataLayer || [];
		function gtag() { dataLayer.push(arguments); }
		gtag('js', new Date());

		gtag('config', 'G-YFBP31Y1CZ');
	</script>
<script type="application/ld+json">
{
 "@context": "https://schema.org",
 "@type": "ItemList",
 "name": "MagCIL open-source code and data",
 "url": "https://magcil.github.io/code.html",
 "itemListElement": [
  {
   "@type": "ListItem",
   "position": 1,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "pyAudioAnalysis",
    "codeRepository": "https://github.com/tyiannak/pyAudioAnalysis",
    "description": "Python library for audio feature extraction, classification, segmentation and applications.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 2,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "deep_audio_features",
    "codeRepository": "https://github.com/tyiannak/deep_audio_features",
    "description": "Training and using CNNs for audio classification, in PyTorch.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 3,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "deepaudio-x",
    "codeRepository": "https://github.com/magcil/deepaudio-x",
    "description": "PyTorch framework for audio classification.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 4,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "deepaudio-lab",
    "codeRepository": "https://github.com/magcil/deepaudio-lab",
    "description": "No-code platform for training, evaluating and deploying deep audio classifiers.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 5,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "amvoc",
    "codeRepository": "https://github.com/tyiannak/amvoc",
    "description": "Analysis of mouse vocal communication.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 6,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "paura",
    "codeRepository": "https://github.com/tyiannak/paura",
    "description": "Real-time audio recording and analysis.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 7,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "multimodal_movie_analysis",
    "codeRepository": "https://github.com/tyiannak/multimodal_movie_analysis",
    "description": "Multimodal analysis of movies and video content.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 8,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "readys",
    "codeRepository": "https://github.com/tyiannak/readys",
    "description": "Assessing speech quality from audio and text.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 9,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "audio-adversarial-attacks",
    "codeRepository": "https://github.com/magcil/audio-adversarial-attacks",
    "description": "Black-box adversarial attacks on sound event classifiers.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 10,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "audio-few-shot-learning",
    "codeRepository": "https://github.com/magcil/audio-few-shot-learning",
    "description": "Prototypical contrastive learning for few-shot audio classification.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 11,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "deep-audio-fingerprinting-benchmark",
    "codeRepository": "https://github.com/magcil/deep-audio-fingerprinting-benchmark",
    "description": "Benchmark for deep audio fingerprinting and song identification.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  },
  {
   "@type": "ListItem",
   "position": 12,
   "item": {
    "@type": "SoftwareSourceCode",
    "name": "GreThE",
    "codeRepository": "https://github.com/magcil/GreThE",
    "description": "A dataset for speech emotion recognition in Greek theatrical plays.",
    "programmingLanguage": "Python",
    "author": {
     "@type": "ResearchOrganization",
     "name": "MagCIL",
     "url": "https://magcil.github.io/"
    }
   }
  }
 ]
}
</script>
</head>

<body class="is-preload">
	<!-- Wrapper -->
	<div id="wrapper">

		<!-- Header -->
		<header id="header">
			<div class="inner">

				<!-- Logo -->
				<a href="index.html" class="logo">
					<span class="symbol"><img src="images/logo.png" alt="MagCIL" /></span><span class="title">Multimodal
						<br>Analysis <br>Group</span>
				</a>

				<span class="affiliations">
					<a href="https://www.iit.demokritos.gr/" target="_blank" rel="noopener">
						<img src="images/logo_iit.png" alt="Institute of Informatics &amp; Telecommunications" /></a>
					<a href="https://www.demokritos.gr/" target="_blank" rel="noopener">
						<img src="images/logo_demokritos.png" alt="NCSR Demokritos" /></a>
				</span>

				<!-- Nav -->
				<nav>
					<ul>
						<li><a href="#menu">Menu</a></li>
					</ul>
				</nav>

			</div>
		</header>

		<!-- Menu -->
		<nav id="menu">
			<h2>Menu</h2>
			<ul>
				<li><a href="index.html">Home</a></li>
				<li><a href="team.html">Team</a></li>
				<li><a href="solutions.html">Research Areas</a></li>
				<li><a href="projects.html">Projects</a></li>
				<li><a href="code.html">Open-source code and data</a></li>
				<li><a href="demos.html">Demos</a></li>
				<li><a href="pub.html">Selected publications</a></li>
				<li><a href="education.html">Education</a></li>
				<li><a href="collaborate.html">Collaborate</a></li>
			</ul>
		</nav>

		<!-- Main -->
		<div id="main">
			<div class="inner">
				<h1>Open source code and data</h1>

				<!-- Text -->
				<section>
					<p>Below you can find some open source tools and libraries in the domain of multimodal signal processing and machine learning, that have been (co)developed by members of our group. For a full list of our open-source repositories visit our GitHub organisation page at <a href="https://github.com/magcil" target="_blank">github.com/magcil</a>.</p>

					<h4>Audio / Speech and Language</h4>

					<div class="table-wrapper">
						<table>
							<tbody>
								<tr>
									<td><a href="https://github.com/magcil/deepaudio-lab" target="_blank">deepaudio-lab</a></td>
									<td>A no-code web platform for training, evaluating and deploying deep audio classifiers. Point it at a
										folder of recordings, configure an experiment through the UI, and it handles training, live monitoring,
										per-class evaluation and packaging into a self-contained inference bundle. Built on top of
										<a href="https://github.com/magcil/deepaudio-x" target="_blank">deepaudio-x</a>, fully containerised for
										on-premises or private-cloud deployment.</td>
									<td>
										<a href="https://github.com/magcil/deepaudio-lab" class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/magcil/deepaudio-x" target="_blank">deepaudio-x</a></td>
									<td>A Python library for training deep audio classifiers using state-of-the-art self-supervised learning backbones (BEATs, PaSST, MobileNet) with minimal code. Supports custom datasets and fine-tuning for downstream audio classification tasks.</td>
									<td>
										<a href="https://github.com/magcil/deepaudio-x" class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/tyiannak/pyAudioAnalysis"
											target="_blank">pyAudioAnalysis</a></td>
									<td>A Python library covering a wide range of audio analysis tasks such as: feature
										extraction, classification, segmentation and clsutering of audio signals</td>
									<td>
										<a href="https://github.com/tyiannak/pyAudioAnalysis"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/tyiannak/deep_audio_features"
											target="_blank">deep-audio-features</a></td>
									<td>A Python library for training Convolutional Neural Netowrks as audio
										classifiers. The library provides wrappers to pytorch for training CNNs on audio
										classification tasks, and using the CNNs as feature extractors.</td>
									<td>
										<a href="https://github.com/tyiannak/deep_audio_features"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/tyiannak/amvoc" target="_blank">amvoc</a></td>
									<td>A Python Tool for Analysis of Mouse Vocal Communication. Developed for (and with
										the help of) <a href="https://jarvislab.net" target="_blank"> Erich Jarvis Lab
											of the Rockefeller University, NY </a></td>
									<td>
										<a href="https://github.com/tyiannak/amvoc"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/tyiannak/paura" target="_blank">paura</a></td>
									<td>A Python AUdio Recording and Analysis Tool, that lets you record sounds from
										your microphone in Python and perform some basic audio analysis in realtime</td>
									<td>
										<a href="https://github.com/tyiannak/paura"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/tyiannak/readys" target="_blank">readys</a></td>
									<td>A Speech Analytics Python Tool for Speech Quality Assessment</td>
									<td>
										<a href="https://github.com/tyiannak/readys"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/magcil/deep-audio-fingerprinting-benchmark"
											target="_blank">Deep-audio-fingerprinting-benchmark</a></td>
									<td>An evaluation benchmark for song identification systems. Code involving deep
										neural architectures, training pipelines, and database indexing techniques for
										developing efficient music recognition systems.</td>
									<td>
										<a href="https://github.com/magcil/deep-audio-fingerprinting-benchmark"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

							</tbody>
						</table>
					</div>


					<h4>Video / Image analysis</h4>

					<div class="table-wrapper">
						<table>
							<tbody>

								<tr>
									<td><a href="https://github.com/tyiannak/multimodal_movie_analysis"
											target="_blank">multimodal movie analysis</a></td>
									<td>A set of scripts to extract features from a movie using audio and visual
										analysis</td>
									<td>
										<a href="https://github.com/tyiannak/multimodal_movie_analysis"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/theopsall/video_annotator"
											target="_blank">video_annotator</a></td>
									<td>A simple video annotator built in task. It can be used for annotating video
										summarization metadata. </td>
									<td>
										<a href="https://github.com/theopsall/video_annotator"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

							</tbody>
						</table>
					</div>

					<h4>General Machine Learning</h4>

					<div class="table-wrapper">
						<table>
							<tbody>
								<tr>
									<td><a href="https://github.com/theopsall/multiSmote" target="_blank">Multilabel
											SMOTE</a></td>
									<td>A Python lib for a multi-label SMOTE dataset upsampling. The implemented
										approach resamples from the representative data that belongs only at the
										minority class.</td>
									<td>
										<a href="https://github.com/theopsall/multiSmote"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/magcil/audio-adversarial-attacks"
											target="_blank">Audio-adversarial-attacks</a></td>
									<td>A repository exploring the vulnerabilities of transformer based architectures
										for sound event classification against adversarial attacks.</td>
									<td>
										<a href="https://github.com/magcil/audio-adversarial-attacks"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/magcil/audio-few-shot-learning"
											target="_blank">Audio-few-shot-learning</a></td>
									<td>A repository evaluating few-shot architectures on audio benchmark datasets.</td>
									<td>
										<a href="https://github.com/magcil/audio-few-shot-learning"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

							</tbody>
						</table>
					</div>


					<h4>Datasets</h4>

					<div class="table-wrapper">
						<table>
							<tbody>



								<tr>
									<td><a href="https://github.com/sofiaele/PuSQ" target="_blank">GreThE</a></td>
									<td>A Dataset for Speech Emotion Recognition in Greek Theatrical Plays</td>
									<td>
										<a href="https://github.com/magcil/GreThE"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/sofiaele/PuSQ" target="_blank">PuSQ</a></td>
									<td>A Public Speaking Quality dataset for assessing the speaker's skills</td>
									<td>
										<a href="https://github.com/sofiaele/PuSQ"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

								<tr>
									<td><a href="https://github.com/theopsall/archeo" target="_blank">archeo</a></td>
									<td>A Python code and a dataset for sound event detection in areas of touristic
										Interest</td>
									<td>
										<a href="https://github.com/theopsall/archeo"
											class="icon brands style2 fa-github"><span class="label">GitHub</span></a>
									</td>
								</tr>

							</tbody>
						</table>
					</div>




				</section>




			</div>
		</div>

		<!-- Footer -->
		<footer id="footer">
			<div class="inner">
				<section>
					<h2>Contact</h2>
					<ul class="icons">
						<li><a href="https://www.linkedin.com/company/75063337/" class="icon brands style2 fa-linkedin"
								target="_blank"><span class="label"></span></a></li>
						<li><a href="mailto:tyiannak@gmail.com" class="icon solid style2 fa-envelope"><span
									class="label">Email</span></a></li>
					</ul>
				</section>
				<ul class="copyright">
					<li>&copy; 2026 MagCIL &middot; Institute of Informatics &amp; Telecommunications, NCSR &quot;Demokritos&quot;</li>
				</ul>
			</div>
		</footer>
	</div>

	<!-- Scripts -->
	<script src="assets/js/jquery.min.js"></script>
	<script src="assets/js/browser.min.js"></script>
	<script src="assets/js/breakpoints.min.js"></script>
	<script src="assets/js/util.js"></script>
	<script src="assets/js/main.js"></script>

</body>

</html>