Browsing by resource type "conference paper"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- BEE-MER: Bimodal Embeddings Ensemble for Music Emotion RecognitionPublication . Lima Louro, Pedro Miguel; Ribeiro, Tiago F. R.; Malheiro, Ricardo; Panda, Renato; Pinto de Carvalho e Paiva, Rui PedroStatic music emotion recognition systems typically focus on audio for classification, although some research has explored the potential of analyzing lyrics as well. Both approaches face challenges when it comes to accurately discerning emotions that have similar energy but differing valence, and vice versa, depending on the modality used. Previous studies have introduced bimodal audio-lyrics systems that outperform single-modality solutions by combining information from standalone systems and conducting joint classification. In this study, we propose and compare two bimodal approaches: one strictly based on embedding models (audio and word embeddings) and another one following a standard spectrogram-based deep learning method for the audio part. Additionally, we explore various information fusion strategies to leverage both modalities effectively. The main conclusions of this work are the following: i) the two approaches show comparable overall classification performance; ii) the embedding-only approach leads to a higher confusion between quadrants 3 and 4 of Russell’s circumplex model; iii) and this approach requires significantly less computational cost for training. We discuss the insights gained from the approaches we experimented with and highlight promising avenues for future research.
- Improving Music Emotion Recognition by Leveraging Handcrafted and Learned FeaturesPublication . Lima Louro, Pedro Miguel; Redinho, Hugo; Malheiro, Ricardo; Panda, Renato; Pinto de Carvalho e Paiva, Rui PedroMusic Emotion Recognition was dominated by classical machine learning, which relies on traditional classifiers and feature engineering (FE). Recently, deep learning approaches have been explored, aiming to remove the need for handcrafted features by automatic feature learning (FL), albeit at the expense of requiring large volumes of data to fully exploit their capabilities. A hybrid approach fusing information from handcrafted and learned features was previously proposed, outperforming separate FE and FL approaches on the 4QAED dataset (900 audio clips). The results suggested that, in smaller datasets, FE and FL could complement each other rather than act as competitors. In the present study, these experiments are extended to the larger MERGE dataset (3554 audio clips) to analyze the impact of the significant increase in data. The best obtained results, 77.62% F1-score, continue to surpass the standalone FE and FL paradigms, reinforcing the potential of hybrid approaches
- Seasonal Variability Of Mode-1 And Mode-2 Internal Solitary Waves Off The Amazon Shelf Observed From Modis/Terra Sunglint ImagesPublication . Macedo, Carina Regina de; Koch-Larrouy, Ariane; Silva, José Carlos B. da; Lentini, 3 Carlos Alessandre D.; Magalhães, Jorge Manuel; Tran, Trung Kien; Rosa, Marcelo Caetano B.; Vantrepotte, VincentThis study focuses on the Amazon ISWs occurrence, their velocity/wavelength, and variability at seasonal cycles. The analysis is based on a data set composed of 71 MODIS/TERRA images, where more than 250 internal solitary wave (ISW) signatures were identified in the sun glint area. ISWs packets separated by typical mode-1 and mode-2 internal tides (ITs) wavelengths have been identified and mapped coming from sites A, and B. In area B, the mode-1 and mode-2 ISWs seem to have lower wavelengths than the ones in area A. Mode-1 ISWs from site A showed higher wave velocity/wavelength during the boreal summer/fall, with higher diversity in terms of propagation velocities. Calculations of the IT velocities using the Taylor-Goldstein equation supported our results of shorter-scale ISWs associated with mode-2 IT wavelengths in the study area and additionally into the ISW/IT seasonal variability.