@inproceedings{
 title = {Emotion and themes recognition in music utilising convolutional and recurrent neural networks},
 type = {inproceedings},
 year = {2019},
 pages = {26-28},
 volume = {2670},
 month = {10},
 day = {27},
 city = {Sophia Antipolis, France},
 id = {9ca1855b-cc5c-3b0f-a768-b9b23805d3af},
 created = {2024-08-09T12:19:55.087Z},
 file_attached = {true},
 profile_id = {ffa9027c-806a-3827-93a1-02c42eb146a1},
 group_id = {da2a8249-fdf4-3036-ba56-7358198a1600},
 last_modified = {2024-08-09T12:20:24.210Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Amiriparian2019},
 source_type = {CONF},
 private_publication = {false},
 abstract = {Emotion is an inherent aspect of music, and associations to music can be made via both life experience and specific musical techniques applied by the composer. Computational approaches for music recognition have been well-established in the research community; however, deep approaches have been limited and not yet comparable to conventional approaches. In this study, we present our fusion system of end-to-end convolutional recurrent neural networks (CRNN) and pre-trained convolutional feature extractors for music emotion and theme recognition1. We train 9 models and conduct various late fusion experiments. Our best performing model (team name: AugLi) achieves 74.2 % ROC-AUC on the test partition which is 1.6 percentage points over the baseline system of the MediaEval 2019 Emotion & Themes in Music task.},
 bibtype = {inproceedings},
 author = {Amiriparian, Shahin and Gerczuk, Maurice and Coutinho, Eduardo and Baird, Alice and Ottl, Sandra and Milling, Manuel and Schuller, Björn},
 booktitle = {CEUR Workshop Proceedings}
}

{"_id":"wMMyEfejA4qP9pein","bibbaseid":"amiriparian-gerczuk-coutinho-baird-ottl-milling-schuller-emotionandthemesrecognitioninmusicutilisingconvolutionalandrecurrentneuralnetworks-2019","authorIDs":["6Z276FjCJdxu2qttA","HmyGQqdmpxNriPHXS","K4xWida4kYEWCujpc","S2CzJg64apkJsPsHA","hzjyyz7CdSRZyRptY","mo4CFXJ7ukAMT9nho","nxyiocLrG567rGYAm","oenDqaFMmkBMZtjuK","tE6ysWmRvSH5uoPFW"],"author_short":["Amiriparian, S.","Gerczuk, M.","Coutinho, E.","Baird, A.","Ottl, S.","Milling, M.","Schuller, B."],"bibdata":{"title":"Emotion and themes recognition in music utilising convolutional and recurrent neural networks","type":"inproceedings","year":"2019","pages":"26-28","volume":"2670","month":"10","day":"27","city":"Sophia Antipolis, France","id":"9ca1855b-cc5c-3b0f-a768-b9b23805d3af","created":"2024-08-09T12:19:55.087Z","file_attached":"true","profile_id":"ffa9027c-806a-3827-93a1-02c42eb146a1","group_id":"da2a8249-fdf4-3036-ba56-7358198a1600","last_modified":"2024-08-09T12:20:24.210Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Amiriparian2019","source_type":"CONF","private_publication":false,"abstract":"Emotion is an inherent aspect of music, and associations to music can be made via both life experience and specific musical techniques applied by the composer. Computational approaches for music recognition have been well-established in the research community; however, deep approaches have been limited and not yet comparable to conventional approaches. In this study, we present our fusion system of end-to-end convolutional recurrent neural networks (CRNN) and pre-trained convolutional feature extractors for music emotion and theme recognition1. We train 9 models and conduct various late fusion experiments. Our best performing model (team name: AugLi) achieves 74.2 % ROC-AUC on the test partition which is 1.6 percentage points over the baseline system of the MediaEval 2019 Emotion & Themes in Music task.","bibtype":"inproceedings","author":"Amiriparian, Shahin and Gerczuk, Maurice and Coutinho, Eduardo and Baird, Alice and Ottl, Sandra and Milling, Manuel and Schuller, Björn","booktitle":"CEUR Workshop Proceedings","bibtex":"@inproceedings{\n title = {Emotion and themes recognition in music utilising convolutional and recurrent neural networks},\n type = {inproceedings},\n year = {2019},\n pages = {26-28},\n volume = {2670},\n month = {10},\n day = {27},\n city = {Sophia Antipolis, France},\n id = {9ca1855b-cc5c-3b0f-a768-b9b23805d3af},\n created = {2024-08-09T12:19:55.087Z},\n file_attached = {true},\n profile_id = {ffa9027c-806a-3827-93a1-02c42eb146a1},\n group_id = {da2a8249-fdf4-3036-ba56-7358198a1600},\n last_modified = {2024-08-09T12:20:24.210Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Amiriparian2019},\n source_type = {CONF},\n private_publication = {false},\n abstract = {Emotion is an inherent aspect of music, and associations to music can be made via both life experience and specific musical techniques applied by the composer. Computational approaches for music recognition have been well-established in the research community; however, deep approaches have been limited and not yet comparable to conventional approaches. In this study, we present our fusion system of end-to-end convolutional recurrent neural networks (CRNN) and pre-trained convolutional feature extractors for music emotion and theme recognition1. We train 9 models and conduct various late fusion experiments. Our best performing model (team name: AugLi) achieves 74.2 % ROC-AUC on the test partition which is 1.6 percentage points over the baseline system of the MediaEval 2019 Emotion & Themes in Music task.},\n bibtype = {inproceedings},\n author = {Amiriparian, Shahin and Gerczuk, Maurice and Coutinho, Eduardo and Baird, Alice and Ottl, Sandra and Milling, Manuel and Schuller, Björn},\n booktitle = {CEUR Workshop Proceedings}\n}","author_short":["Amiriparian, S.","Gerczuk, M.","Coutinho, E.","Baird, A.","Ottl, S.","Milling, M.","Schuller, B."],"urls":{"Paper":"https://bibbase.org/service/mendeley/ffa9027c-806a-3827-93a1-02c42eb146a1/file/2dcac6f9-e21a-9671-62f8-104083bd621f/2019___Amiriparian_et_al___Emotion_and_themes_recognition_in_music_utilising_convolutional_and_recurrent_neural_networks.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/ffa9027c-806a-3827-93a1-02c42eb146a1","bibbaseid":"amiriparian-gerczuk-coutinho-baird-ottl-milling-schuller-emotionandthemesrecognitioninmusicutilisingconvolutionalandrecurrentneuralnetworks-2019","role":"author","metadata":{"authorlinks":{"baird, a":"https://aliceebaird.github.io/publications.html","coutinho, e":"https://bibbase.org/service/mendeley/ffa9027c-806a-3827-93a1-02c42eb146a1"}},"downloads":0},"bibtype":"inproceedings","creationDate":"2020-05-29T15:18:52.742Z","downloads":0,"keywords":[],"search_terms":["emotion","themes","recognition","music","utilising","convolutional","recurrent","neural","networks","amiriparian","gerczuk","coutinho","baird","ottl","milling","schuller"],"title":"Emotion and themes recognition in music utilising convolutional and recurrent neural networks","year":2019,"biburl":"https://bibbase.org/service/mendeley/ffa9027c-806a-3827-93a1-02c42eb146a1","dataSources":["YqW8pMoihb7JazZcx","fra8PtjojQb2HvrNt"]}