Suchergebnisse

The concept of spatial synchrony in ecology refers to the presence of coordinated time fluctuations in certain characteristics that can be observed in plant and animal communities inhabiting an area. It is a well-known phenomenon common to virtually every taxon, but comparatively little attention has been given to the study of the temporal coherence of forest tree performance across biogeographical gradients. In forest ecosystems, tree growth dynamics is primarily driven by climatic variability (i.e., the Moran effect). Due to rapid climate change, trees are increasingly pushed to their physiological limits up to the level that many populations are facing immediate risk of extinction. The characterization of synchrony patterns in tree growth can provide clues on the relevance of emerging climatic threats on forests, as new combinations of precipitation and temperature are entraining tree performance worldwide. In this regard, comprehensive and systematic approaches to analyse spatiotemporal dynamics of tree growth are needed. Here, we present a methodology for disentangling and interpreting how the variability and common signal strength of tree growth (or other traits) are structured in tree-ring networks. It is grounded on mixed modelling principles and broadens well-known theoretical principles in dendrosciences. Based on this approach, we describe the essential properties of spatial synchrony in tree growth at multiple geographical scales. We also discuss the potential of this methodology to discern early warning signals of climate change impacts on forest ecosystems. ; T.A.S. acknowledges support of ERANET-Mundus (European Commission). This study was supported by the project 2014 SGR1141 (Catalan Government).

We provide a survey of the field of Music Information Retrieval (MIR), in particular paying attention to latest developments, such as semantic auto-tagging and user-centric retrieval and recommendation approaches. We first elaborate on well-established and proven methods for feature extraction and music indexing, from both the audio signal and contextual data sources about music items, such as web pages or collaborative tags. These in turn enable a wide variety of music retrieval tasks, such as semantic music search or music identification ("query by example"). Subsequently, we review current work on user analysis and modeling in the context of music recommendation and retrieval, addressing the recent trend towards user-centric and adaptive approaches and systems. A discussion follows about the important aspect of how various MIR approaches to different problems are evaluated and compared. Eventually, a discussion about the major open challenges concludes the survey. ; This work is supported by the Austrian Science Fund (FWF): P22856 and P25655, as well as by the European Union Seventh Framework Programme FP7 / 2007-2013 through the PHENICX project under grant agreement no. 601166, the A4U postdoctoral grants programme, and the Junta of Andalusia through the COFLA2 project (P12-TIC-1362). The authors would further like to thank Masataka Goto, Mohamed Sordo, and Edith Law for granting permission to include their visual material in this survey, and Juan J. Bosch for his comments on the manuscript. Furthermore, the authors would like to express their gratitude to the anonymous reviewers for their highly valuable suggestions for improving the manuscript.

Comunicació presentada al 1st Workshop on Designing Human-Centric MIR Systems celebrat el 2 de novembre de 2019 a Delft, Països Baixos, en el marc del 20th annual conference of the International Society for Music Information Retrieval (ISMIR). ; Music recommendations are increasingly part of the listening experience of people all over the world, especially in the context of streaming services. In this scenario, recommender systems' role is to help users in finding music that can fit their interests and tastes. However, Westerncentric perspectives in systems' design are often subject to criticisms because of their power of reinforcing already existing cultural bias and therefore potentially impacting negatively on the music distribution mechanisms. In our research proposal, we aim to address the problem of assessing the impact of music recommendation diversity, or the lack thereof. This requires 1) the formalization of a working definition of diversity in the music field 2) the development of evaluation practices for estimating diversity in the context of music recommender systems 3) the observation of emerging impact due to music recommendation diversity 4) the proposal of countermeasures for mitigating negative or reinforcing positive impact observed. Basing on already known consequences of information technologies in political, economic and social areas, our goal is to understand the cultural impact that music recommender systems can have on our society. ; This work is partially supported by the European Commission under the TROMPA project (H2020 770376).

Comunicació presentada a: International Society for Music Information Retrieval Conference celebrat de l'11 al 16 d'octubre de 2020 de manera virtual. ; Version identification systems aim to detect different renditions of the same underlying musical composition (loosely called cover songs). By learning to encode entire recordings into plain vector embeddings, recent systems have made significant progress in bridging the gap between accuracy and scalability, which has been a key challenge for nearly two decades. In this work, we propose to further narrow this gap by employing a set of data distillation techniques that reduce the embedding dimensionality of a pre-trained state-of-the-art model. We compare a wide range of techniques and propose new ones, from classical dimensionality reduction to more sophisticated distillation schemes. With those, we obtain 99% smaller embeddings that, moreover, yield up to a 3% accuracy increase. Such small embeddings can have an important impact in retrieval time, up to the point of making a real-world system practical on a standalone laptop. ; This work is supported by the MIP-Frontiers project, the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 765068, and by TROMPA, the Horizon 2020 project 770376-2.

The version identification (VI) task deals with the automatic detection of recordings that correspond to the same underlying musical piece. Despite many efforts, VI is still an open problem, with much room for improvement, specially with regard to combining accuracy and scalability. In this paper, we present MOVE, a musically-motivated method for accurate and scalable version identification. MOVE achieves state-of-the-art performance on two publicly-available benchmark sets by learning scalable embeddings in an Euclidean distance space, using a triplet loss and a hard triplet mining strategy. It improves over previous work by employing an alternative input representation, and introducing a novel technique for temporal content summarization, a standardized latent space, and a data augmentation strategy specifically designed for VI. In addition to the main results, we perform an ablation study to highlight the importance of our design choices, and study the relation between embedding dimensionality and model performance. ; Comunicació presentada a: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, celebrat en línia del 4 al 8 de maig de 2020. ; This work is supported by the MIP-Frontiers project, the European Union's Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No. 765068, and by TROMPA, the Horizon 2020 project 770376-2.

Metaphors are commonly used in interface design within Human-Computer Interaction (HCI). Interface metaphors provide users with a way to interact with the computer that resembles a known activity, giving instantaneous knowledge or intuition about how the interaction works. A widely used one in Digital Musical Instruments (DMIs) is the conductor-orchestra metaphor, where the orchestra is considered as an instrument controlled by the movements of the conductor. We propose a DMI based on the conductor metaphor that allows to control tempo and dynamics and adapts its mapping specifically for each user by observing spontaneous conducting movements (i.e., movements performed on top of fixed music without any instructions). We refer to this as mapping by observation given that, even though the system is trained specifically for each user, this training is not done explicitly and consciously by the user. More specifically, the system adapts its mapping based on the tendency of the user to anticipate or fall behind the beat and observing the Motion Capture descriptors that best correlate to loudness during spontaneous conducting. We evaluate the proposed system in an experiment with twenty four (24) participants where we compare it with a baseline that does not perform this user-specific adaptation. The comparison is done in a context where the user does not receive instructions and, instead, is allowed to discover by playing. We evaluate objective and subjective measures from tasks where participants have to make the orchestra play at different loudness levels or in synchrony with a metronome. Results of the experiment prove that the usability of the system that automatically learns its mapping from spontaneous movements is better both in terms of providing a more intuitive control over loudness and a more precise control over beat timing. Interestingly, the results also show a strong correlation between measures taken from the data used for training and the improvement introduced by the adapting system. This indicates that it is possible to estimate in advance how useful the observation of spontaneous movements is to build user-specific adaptations. This opens interesting directions for creating more intuitive and expressive DMIs, particularly in public installations. ; This work was supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the PHENICX project (grant agreement no. 601166) and by the CASAS project (TIN2015-70816-R).

The extraction of pitch information is arguably one of the most important tasks in automatic music description systems. However, previous research and evaluation datasets dealing with pitch estimation focused on relatively limited kinds of musical data. This work aims to broaden this scope by addressing symphonic western classical music recordings, focusing on pitch estimation for melody extraction. This material is characterized by a high number of overlapping sources, and by the fact that the melody may be played by different instrumental sections, often alternating within an excerpt. We evaluate the performance of eleven state-of-the-art pitch salience functions, multipitch estimation and melody extraction algorithms when determining the sequence of pitches corresponding to the main melody in a varied set of pieces. An important contribution of the present study is the proposed evaluation framework, including the annotation methodology, generated dataset and evaluation metrics. The results show that the assumptions made by certain methods hold better than others when dealing with this type of music signal, leading to a better performance. Additionally, we propose a simple method for combining the output of several algorithms, with promising results. ; This work is supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the PHENICX project (grant agreement no. 601166). This work is also (partly) supported by the Spanish Ministry of Economy and Competitiveness/nunder the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).

High-latitude terrestrial ecosystems are crucial to the global climate system and its regulation by vegetation. Since productivity of boreal forests is much limited by low summer temperatures, it is expected that trees subjected to warming are progressively decreasing their regional growth coherence in the last decades. In this study, we used a comprehensive network of indexed ring-width records to assess 20th-century spatiotemporal patterns of climatic sensitivity of forest growth around the Urals mountain range above 60 °N (ca. 750,000 km2). This area offers an excellent opportunity to test for warming effects as most north Eurasian conifers (including Larix, Picea and Pinus species) are found along a north-to-south temperature gradient across contrasting soil hydrothermal regimes (permafrost and permafrost-free). We observed positive associations between indexed ring-width and summer temperature over the past century, decreasing southwards. However, weaker (permafrost) or non-significant (permafrost-free) relationships were consistently found at the local and regional scales after 1960. A cointegration analysis indicated that tree-growth release from cold limitation significantly reduced the degree and spatial extent of synchronous growth at short- (annual) and long-term (decadal) scales, most likely by exposing forests to endogenous (local) factors (e.g., competition, soil properties, nutrient availability) and species-specific reactions. Whereas the loss of temperature sensitivity progressively reduced non-permafrost synchrony by 50% over the whole 20th century, permafrost forests decreased their synchrony only after the 1960s, by 20%. Radial growth was enhanced in permafrost sites, as suggested by increasing basal area increment. Our results unequivocally link a substantial decrease in temporal coherence of forest productivity in boreal ecosystems to a growth release from cold limitation that is concurrent with regional warming trends. This emerging pattern points to increasing dependence on local drivers of the carbon balance and the role as carbon sinks of forests in the northern Ural region. ; This study was funded by the European Union's Seventh Framework Programme (INTERACT project), grant agreement SYNCHROTREES, the Spanish Government (grant number AGL2015-68274-C3-3-R) and the Russian Science Foundation (project number 18-14-00072).

Comunicació presentada a: International Society for Music Information Retrieval Conference celebrat de l'11 al 16 d'octubre de 2020 de manera virtual. ; Recent works have addressed the automatic cover detection problem from a metric learning perspective. They employ different input representations, aiming to exploit melodic or harmonic characteristics of songs and yield promising performances. In this work, we propose a comparative study of these different representations and show that systems combining melodic and harmonic features drastically outperform those relying on a single input representation. We illustrate how these features complement each other with both quantitative and qualitative analyses. We finally investigate various fusion schemes and propose methods yielding state-of-the-art performances on two publicly-available large datasets. ; FY is supported by the MIP-Frontiers project, the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 765068, and EG by TROMPA, the Horizon 2020 project 770376-2.

This work focuses on the topic of melodic characterization and similarity in a specific musical repertoire: a cappella flamenco singing, more specifically in debla and martinete styles. We propose the combination of manual and automatic description. First, we use a state-of-the-art automatic transcription method to account for general melodic similarity from music recordings. Second, we define a specific set of representative mid-level melodic features, which are manually labelled by flamenco experts. Both approaches are then contrasted and combined into a global similarity measure. This similarity measure is assessed by inspecting the clusters obtained through phylogenetic algorithms and by relating similarity to categorization in terms of style. Finally, we discuss the advantage of combining automatic and expert annotations as well as the need to include repertoire-specific descriptions for meaningful melodic characterization in traditional music collections. ; This article has been funded by the Andalusian Government under a Proyecto de Excelencia research project with reference number P12-TIC-1362.

Comunicació presentada al Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017), celebrat el dia 16 de novembre de 2017 a Munic, Alemanya. ; This work describes our contribution to the acoustic scene classifi- cation task of the DCASE 2017 challenge. We propose a system that consists of the ensemble of two methods of different nature: a feature engineering approach, where a collection of hand-crafted features is input to a Gradient Boosting Machine, and another approach based on learning representations from data, where log-scaled melspectrograms are input to a Convolutional Neural Network. This CNN is designed with multiple filter shapes in the first layer. We use a simple late fusion strategy to combine both methods. We report classification accuracy of each method alone and the ensemble system on the provided cross-validation setup of TUT Acoustic Scenes 2017 dataset. The proposed system outperforms each of its component methods and improves the provided baseline system by 8.2%. ; This work is partially supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 688382 "AudioCommons", and the European Research Council under the European Union's Seventh Framework Program, as part of the CompMusic project (ERC grant agreement 267583), and the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).

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).

1. Climate warming increases vulnerability to drought in Mediterranean water-limited forests. However, we still lack knowledge of the long-term physiological responses of coexisting pine species in these forests regarding their ability to cope with warming-induced drought stress. 2. We investigated spatiotemporal patterns of tree performance for five isohydric pines with partially overlapping ecological niches in the eastern Iberian Peninsula along an altitudinal gradient: Pinus halepensis = Pinus pinaster ≤ Pinus nigra ≤ Pinus sylvestris ≤ Pinus uncinata. 3. Using indexed tree-ring widths (TRWi), we assessed the changes in the temporal coherence of radial growth (growth synchrony, âC) over the period 1902-2011 across three elevation belts: low ≈1100 m; mid = 1615 m; high = 2020 m. We also examined by mixed modelling whether TRWi showed an increased coupling with leaf-level gas exchange (inferred from indexed carbon isotope discrimination, Δ13Ci) by enhanced stomatal regulation in response to an amplified regional drought stress. 4. Increasingly negative annual water balances (decrease in annual precipitation minus evapotranspiration = −4·8 mm year−1; 1970-2011) prompted more synchronous growth of coexisting pines between low- and mid-elevation belts, with âC rising from 0·25 ± 0·04 (1902-1951) to 0·62 ± 0·05 (1962-2011). This effect was coupled with tighter stomatal regulation at mid-elevation as indicated by high correlations between TRWi and Δ13Ci (>0·60 from the mid-1970s onwards) which resembled those found at low elevation. Simultaneously, TRWi vs. Δ13Ci uncoupling occurred at the high-elevation belt across species. 5.Weaker growth-climate relationships as elevation increased highlighted the major role of the altitude-dependent thermal gradient in growth responsiveness to drought; however, an intensified Δ13Ci response to spring water availability across elevation belts observed from mid-1970s onwards suggested regional shifts in tree physiological activity linked to earlier seasonal drought impacts. Warming-induced drought stress is spreading to higher altitudes in Iberian pinewoods as multispecies growth is linked to progressively tighter stomatal control of water losses reflected in wood Δ13C. ; T.A.S. and J.P.F acknowledge ERANET-Mundus (European Commission, Grant agreement 20112573) and the Ramón y Cajal program (RYC-2008-02050) respectively. A.A.K. benefitted from a visiting grant (University of Lleida). This study was supported by projects AGL2015-68274-C3-3-R (MINECO/FEDER) and 2014 SGR1141 (Catalan Government). We acknowledge P. Sopeña and M.J. Pau for technical assistance and G. Sangüesa-Barreda for field sampling.

This study deals with the strong relationship between emotions and music, investigating three main research questions: (RQ1) Are there differences in human music perception (e.g., emotions, tempo, instrumentation, and complexity), according to musical education, experience, demographics, and personality traits?; (RQ2) Do certain perceived music characteristics correlate (e.g., tension and sadness), irrespective of a particular listener's background or personality?; (RQ3) Does human perception of music characteristics, such as emotions and tempo, correlate with descriptors extracted from music audio signals? To investigate our research questions, we conducted two user studies focusing on different groups of subjects. We used web-based surveys to collect information about demographics, listening habits, musical education, personality, and perceptual ratings with respect to perceived emotions, tempo, complexity, and instrumentation for 15 segments of Beethoven's 3rd symphony, "Eroica". Our experiments showed that all three research questions can be affirmed, at least partly. We found strong support for RQ2 and RQ3, while RQ1 could be confirmed only for some perceptual aspects and user groups. ; This research is supported by the EU-FP7 project no. 601166 ("PHENICX"), the Austrian Science Fund (FWF): P25655 and the Spanish Government (CASAS project TIN2015-70816-R).

Comunicació presentada a: 20th annual conference of the International Society for Music Information Retrieval (ISMIR) celebrat del 4 al 8 de novembre de 2019 a Delft, Països Baixos. ; This paper focuses on Cover Song Identification (CSI), an important research challenge in content-based Music Information Retrieval (MIR). Although the task itself is interesting and challenging for both academia and industry scenarios, there are a number of limitations for the advancement of current approaches. We specifically address two of them in the present study. First, the number of publicly available datasets for this task is limited, and there is no publicly available benchmark set that is widely used among researchers for comparative algorithm evaluation. Second, most of the algorithms are not publicly shared and reproducible, limiting the comparison of approaches. To overcome these limitations we propose Da-TACOS, a DaTAset for COver Song Identification and Understanding, and two frameworks for feature extraction and benchmarking to facilitate reproducibility. Da-TACOS contains 25K songs represented by unique editorial metadata plus 9 low- and mid-level features pre-computed with open source libraries, and is divided into two subsets. The Cover Analysis subset contains audio features (e.g. key, tempo) that can serve to study how musical characteristics vary for cover songs. The Benchmark subset contains the set of features that have been frequently used in CSI research, e.g. chroma, MFCC, beat onsets etc. Moreover, we provide initial benchmarking results of a selected number of state-of-the-art CSI algorithms using our dataset, and for reproducibility, we share a GitHub repository containing the feature extraction and benchmarking frameworks. ; This work is partially supported by the MIP-Frontiers project, the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 765068, and by TROMPA, the Horizon 2020 project 770376-2.