{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:39:27Z","timestamp":1760402367305,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T00:00:00Z","timestamp":1586908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The current paper focuses on the investigation of spoken-language classification in audio broadcasting content. The approach reflects a real-word scenario, encountered in modern media\/monitoring organizations, where semi-automated indexing\/documentation is deployed, which could be facilitated by the proposed language detection preprocessing. Multilingual audio recordings of specific radio streams are formed into a small dataset, which is used for the adaptive classification experiments, without seeking\u2014at this step\u2014for a generic language recognition model. Specifically, hierarchical discrimination schemes are followed to separate voice signals before classifying the spoken languages. Supervised and unsupervised machine learning is utilized at various windowing configurations to test the validity of our hypothesis. Besides the analysis of the achieved recognition scores (partial and overall), late integration models are proposed for semi-automatically annotation of new audio recordings. Hence, data augmentation mechanisms are offered, aiming at gradually formulating a Generic Audio Language Classification Repository. This database constitutes a program-adaptive collection that, beside the self-indexing metadata mechanisms, could facilitate generic language classification models in the future, through state-of-art techniques like deep learning. This approach matches the investigatory inception of the project, which seeks for indicators that could be applied in a second step with a larger dataset and\/or an already pre-trained model, with the purpose to deliver overall results.<\/jats:p>","DOI":"10.3390\/info11040211","type":"journal-article","created":{"date-parts":[[2020,4,16]],"date-time":"2020-04-16T05:15:41Z","timestamp":1587014141000},"page":"211","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Investigation of Spoken-Language Detection and Classification in Broadcasted Audio Content"],"prefix":"10.3390","volume":"11","author":[{"given":"Rigas","family":"Kotsakis","sequence":"first","affiliation":[{"name":"School of Journalism and Mass Communications, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0697-8531","authenticated-orcid":false,"given":"Maria","family":"Matsiola","sequence":"additional","affiliation":[{"name":"School of Journalism and Mass Communications, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Kalliris","sequence":"additional","affiliation":[{"name":"School of Journalism and Mass Communications, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7923-9361","authenticated-orcid":false,"given":"Charalampos","family":"Dimoulas","sequence":"additional","affiliation":[{"name":"School of Journalism and Mass Communications, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,4,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1016\/j.specom.2012.01.004","article-title":"Investigation of broadcast-audio semantic analysis scenarios employing radio-programme-adaptive pattern classification","volume":"54","author":"Kotsakis","year":"2012","journal-title":"Speech Commun."},{"unstructured":"Kotsakis, R., Kalliris, G., and Dimoulas, C. (2012, January 26\u201329). Investigation of salient audio-features for pattern-based semantic content analysis of radio productions. Proceedings of the 132nd AES Convention, Budapest, Hungary.","key":"ref_2"},{"doi-asserted-by":"crossref","unstructured":"Kotsakis, R.G., Dimoulas, C.A., and Kalliris, G.M. (2012, January 3\u20134). Contribution of Stereo Information to Feature-Based Pattern Classification for Audio Semantic Analysis. Proceedings of the 2012 Seventh International Workshop on Semantic and Social Media Adaptation and Personalization, Luxembourg.","key":"ref_3","DOI":"10.1109\/SMAP.2012.26"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"66","DOI":"10.17743\/jaes.2019.0058","article-title":"1D\/2D Deep CNNs vs. Temporal Feature Integration for General Audio Classification","volume":"68","author":"Vrysis","year":"2020","journal-title":"J. Audio Eng. Soc."},{"unstructured":"Thoidis, I., Vrysis, L., Pastiadis, K., Markou, K., and Papanikolaou, G. (2019). Investigation of an Encoder-Decoder LSTM model on the enhancement of speech intelligibility in noise for hearing-impaired listeners. Audio Engineering Society Convention 146, Audio Engineering Society.","key":"ref_5"},{"unstructured":"Kostek, B. (2005). Perception-Based Data Processing in Acoustics: Applications to Music Information Retrieval and Psychophysiology of Hearing, Springer.","key":"ref_6"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.17743\/jaes.2018.0066","article-title":"Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition","volume":"66","author":"Korvel","year":"2018","journal-title":"J. Audio Eng. Soc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7","DOI":"10.17743\/jaes.2019.0045","article-title":"Toward Language-Agnostic Speech Emotion Recognition","volume":"68","author":"Ntalampiras","year":"2020","journal-title":"J. Audio Eng. Soc."},{"unstructured":"Vrysis, L., Tsipas, N., Dimoulas, C., and Papanikolaou, G. (2017). Extending Temporal Feature Integration for Semantic Audio Analysis. Audio Engineering Society Convention 142, Audio Engineering Society.","key":"ref_9"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"410","DOI":"10.3390\/acoustics1020023","article-title":"An Enhanced Temporal Feature Integration Method for Environmental Sound Recognition","volume":"1","author":"Bountourakis","year":"2019","journal-title":"Acoustics"},{"unstructured":"Dimoulas, C., Vegiris, C., Avdelidis, K., Kalliris, G., and Papanikolaou, G. (2007, January 5\u20138). Automated Audio Detection, Segmentation, and Indexing with Application to Postproduction Editing. Proceedings of the 122nd AES Convention, Vienna, Austria.","key":"ref_11"},{"unstructured":"Vegiris, C., Dimoulas, C., and Papanikolaou, G. (2009, January 7\u201310). Audio Content Annotation, Description and Management Using Joint Audio Detection, Segmentation and Classification Techniques. Proceedings of the 126th AES Convention, Munich, Germany.","key":"ref_12"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.17743\/jaes.2016.0051","article-title":"Crowdsourcing audio semantics by means of hybrid bimodal segmentation with hierarchical classification","volume":"64","author":"Vrysis","year":"2016","journal-title":"J. Audio Eng. Soc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"244","DOI":"10.17743\/jaes.2014.0014","article-title":"Forensic Automatic Speaker Recognition with Degraded and Enhanced Speech","volume":"62","author":"Alexander","year":"2014","journal-title":"J. Audio Eng. Soc."},{"doi-asserted-by":"crossref","unstructured":"Korvel, G., Treigys, P., Tamulevi\u010dius, G., Bernatavi\u010dien\u0117, J., and Bo\u017cena, K. (2019). Borrowing 2D Feature Maps from Audio Signal Analysis to Deep Learning-based Speech Recognition. J. Audio Eng. Soc., (accepted, in editorial process).","key":"ref_15","DOI":"10.17743\/jaes.2018.0066"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/TASL.2006.878261","article-title":"Multistage speaker diarization of broadcast news","volume":"14","author":"Barras","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Zewoudie, A.W., Luque, I., and Hernando, J. (2018). The use of long-term features for GMM-and i-vector-based speaker diarization systems. EURASIP J. Audio Speech Music Process.","key":"ref_17","DOI":"10.1186\/s13636-018-0140-x"},{"doi-asserted-by":"crossref","unstructured":"Shi, Y., Zhou, J., Long, Y., Li, Y., and Mao, H. (2019). Addressing Text-Dependent Speaker Verification Using Singing Speech. Appl. Sci., 9.","key":"ref_18","DOI":"10.3390\/app9132636"},{"doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., and Khudanpur, S. (2018, January 15\u201320). X-vectors: Robust DNN embeddings for speaker recognition. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","key":"ref_19","DOI":"10.1109\/ICASSP.2018.8461375"},{"unstructured":"Dimoulas, C., and Kalliris, G. (2013, January 4\u20137). Investigation \u03bff wavelet approaches for joint temporal, spectral and cepstral features in audio semantics. Proceedings of the 134th AES Convention, Rome, Italy.","key":"ref_20"},{"key":"ref_21","first-page":"571","article-title":"A robust and computationally efficient speech\/music discriminator","volume":"54","author":"Barbedo","year":"2006","journal-title":"J. Audio Eng. Soc."},{"doi-asserted-by":"crossref","unstructured":"Tsipas, N., Vrysis, L., Dimoulas, C., and Papanikolaou, G. (2017). Efficient audio-driven multimedia indexing through similarity-based speech\/music discrimination. Multimed. Tools Appl., 1\u201319.","key":"ref_22","DOI":"10.1007\/s11042-016-4315-0"},{"unstructured":"Tsipas, N., Vrysis, L., Dimoulas, C., and Papanikolaou, G. (2015, January 7\u201310). Content-Based Music Structure Analysis using Vector Quantization. Proceedings of the 138th AES Convention, Warsaw, Poland.","key":"ref_23"},{"unstructured":"Hellmuth, O., Allamanche, E., Kastner, J.H.T., Lefebvre, N., and Wistorf, R. (2004, January 17\u201319). Music Genre Estimation from Low Level Audio Features. Proceedings of the 25th AES International Conference, London, UK.","key":"ref_24"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MMUL.2015.33","article-title":"Syncing Shared Multimedia through Audiovisual Bimodal Segmentation","volume":"22","author":"Dimoulas","year":"2015","journal-title":"IEEE Multimed."},{"doi-asserted-by":"crossref","unstructured":"Lerch, A. (2012). An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics, John Wiley & Sons.","key":"ref_26","DOI":"10.1002\/9781118393550"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"457","DOI":"10.17743\/jaes.2018.0036","article-title":"Speech Emotion Recognition for Performance Interaction","volume":"66","author":"Vryzas","year":"2018","journal-title":"J. Audio Eng. Soc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"14","DOI":"10.17743\/jaes.2019.0043","article-title":"Continuous Speech Emotion Recognition with Convolutional Neural Networks","volume":"68","author":"Vryzas","year":"2020","journal-title":"J. Audio Eng. Soc."},{"key":"ref_29","first-page":"62","article-title":"Emotional Prediction and Content Profile Estimation in Evaluating Audiovisual Mediated Communication","volume":"2","author":"Kotsakis","year":"2014","journal-title":"Int. J. Monit. Surveill. Technol. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.neucom.2016.03.020","article-title":"An overview of applications and advancements in automatic sound recognition","volume":"200","author":"Sharan","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7421","DOI":"10.1007\/s11042-016-3386-2","article-title":"Ensemble audio segmentation for radio and television programmes","volume":"76","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.patcog.2019.03.016","article-title":"Learning sound representations using trainable COPE feature extractors","volume":"92","author":"Strisciuglioa","year":"2019","journal-title":"Pattern Recognition."},{"unstructured":"Kotsakis, R., Kalliris, G., and Dimoulas, C. (2020). Extending radio broadcasting semantics through adaptive audio segmentation automations. Multimed. Tools Appl., (prepared for submission).","key":"ref_33"},{"key":"ref_34","first-page":"1","article-title":"Language choice and language attitudes in a multilingual Arab Canadian community: Quebec-Canada: A sociolinguistic study","volume":"3","author":"Dweik","year":"2015","journal-title":"Br. J. Engl. Linguist."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.aej.2016.12.009","article-title":"Speaker diarization system using HXLPS and deep neural network","volume":"57","author":"Ramaiah","year":"2018","journal-title":"Alex. Eng. J."},{"doi-asserted-by":"crossref","unstructured":"Kotsakis, R., Mislow, A., Kalliris, G., and Matsiola, M. (2015, January 7\u20139). Feature-Based Language Discrimination in Radio Productions via Artificial Neural Training. Proceedings of the 10th Audio Mostly, ACM, New York, NY, USA.","key":"ref_36","DOI":"10.1145\/2814895.2814928"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1109\/TASLP.2015.2419978","article-title":"Rapid Language Identification","volume":"23","author":"Segbroeck","year":"2015","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Leonard, R.G., and Doddington, G.R. (1978). Doddington, Automatic Language Discrimination, Texas Instruments Inc.. No. TI-08-77-46.","key":"ref_38","DOI":"10.21236\/ADA050841"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/79.317925","article-title":"Reviewing automatic language identification","volume":"11","author":"Muthusamy","year":"1994","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.csl.2005.06.003","article-title":"Support vector machines for speaker and language recognition","volume":"20","author":"Campbell","year":"2006","journal-title":"Comput. Speech Lang."},{"doi-asserted-by":"crossref","unstructured":"Kuncheva, L.I. (2004). Combining Pattern Classifiers: Methods and Algorithms, John Wiley & Sons.","key":"ref_41","DOI":"10.1002\/0471660264"},{"unstructured":"Brachman, R.J., and Dietterich, T.G. (2009). Introduction to Semi-supervised Learning. Synthesis Lectures on Artificial Intelligence ad Machine Learning, Morgan & Claypool Publishers.","key":"ref_42"},{"unstructured":"Lartillot, O., and Toiviainen, P. (2007, January 23\u201327). Mir in matlab (ii): A toolbox for musical feature extraction from audio. Proceedings of the 8th International Conference on Music Information Retrieval, Vienna, Austria.","key":"ref_43"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The WEKA Data Mining Software: An Update","volume":"11","author":"Hall","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"unstructured":"Zim, H.S. (1967). Codes & Secret Writing: Authorized Abridgement, Scholastic Book Service.","key":"ref_45"},{"unstructured":"(2020, April 14). English Letter Frequency Counts: Mayzner Revisited or Etaoin Srhldcu. Available online: https:\/\/norvig.com\/mayzner.html.","key":"ref_46"},{"unstructured":"(2020, April 14). Corpus de Thomas Temp\u00e9. Archived from the original on 30 September 2007. Available online: https:\/\/web.archive.org\/web\/20070930194046\/http:\/\/gpl.insa-lyon.fr\/Dvorak-Fr\/CorpusDeThomasTemp%C3%A9.","key":"ref_47"},{"unstructured":"Beutelspacher, A. (2014). Kryptologie, Vieweg. [7th ed.].","key":"ref_48"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/4\/211\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:30:50Z","timestamp":1760362250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/4\/211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,15]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,4]]}},"alternative-id":["info11040211"],"URL":"https:\/\/doi.org\/10.3390\/info11040211","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2020,4,15]]}}}