Suchergebnisse

Comunicació presentada al workshop Human Centered AI inclòs a: 35th Conference on Neural Information Processing Systems (NeurIPS 2021) celebrat el 13 de desembre de manera virtual. ; This work presents an initial proof of concept of how Music Emotion Recognition (MER) systems could be intentionally biased with respect to annotations of musically-induced emotions in a political context. In specific, we analyze traditional Colombian music containing politically-charged lyrics of two types: (1) vallenatos and social songs from the "left-wing" guerrilla Fuerzas Armadas Revolucionarias de Colombia (FARC) and (2) corridos from the "right-wing" paramilitaries Autodefensas Unidas de Colombia (AUC). We train personalized machine learning models to predict induced emotions for three users with diverse political views – we aim at identifying the songs that may induce negative emotions for a particular user, such as anger and fear. To this extent, a user's emotion judgements could be interpreted as problematizing data – subjective emotional judgments could in turn be used to influence the user in a human-centered machine learning environment. In short, highly desired "emotion regulation" applications could potentially deviate to "emotion manipulation" – the recent discredit of emotion recognition technologies might transcend ethical issues of diversity and inclusion. ; The research work conducted at the Universitat Pompeu Fabra is partially supported by the Eu- ropean Commission under the TROMPA project (H2020 770376) and the Project Musical AI - PID2019-111403GB-I00/AEI/10.13039/501100011033 funded by the Spanish Ministerio de Ciencia, Innovación y Universidades (MCIU) and the Agencia Estatal de Investigación (AEI).

Comunicació presentada a: the 16th International Society for Music Information Retrieval Conference (ISMIR), celebrat del 26 al 30 d'octubre de 2015 a Màlaga. ; We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products. ; This work is supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the GiantSteps project (grant agreement no. 610591).