- 120
- 304 704
MusicTechnologyGroup
Spain
เข้าร่วมเมื่อ 3 มิ.ย. 2008
Research group specialised in audio signal processing, music information retrieval, musical interfaces, and computational musicology. The Music Technology Group (MTG) is part of the Department of Information and Communication Technologies at the Universitat Pompeu Fabra in Barcelona. The MTG wants to contribute to the improvement of the information and communication technologies related to sound and music, carrying out competitive research at the international level and at the same time transferring its results to society. To that goal, the MTG aims at finding a balance between basic and applied research while promoting interdisciplinary approaches that incorporate knowledge and methodologies from both scientific/technological and humanistic/artistic disciplines.
Studying a Musical Repertoire with Computational Approaches: The Case of Carnatic Music
Seminar by Xavier Serra at RITMO's Seminar Series (December 3rd, 2024)
Abstract:
In this talk, we will explore our extensive research efforts in applying computational methodologies to analyze and understand diverse music traditions, with a focus on Carnatic music. We will delve into the journey from identifying research questions to disseminating impactful results, highlighting the collaborative process with musicians, scholars, and technologists within the Carnatic music community. This presentation will address various facets of our work, including the curation and creation of culturally rich datasets, the development of tailored signal processing and machine learning techniques, and the unique challenges we encountered in capturing the nuanced characteristics of Carnatic music. We will discuss specific tasks such as audio source separation and melodic analysis, showcasing the methodologies and tools designed to address the complex, ornamented structures of Carnatic music.
The talk will also cover evaluation frameworks that measure the relevance and accuracy of our findings, as well as the development of practical applications that support both academic research and broader community engagement. Finally, we will reflect on the broader implications of this research, considering its impact on the preservation and understanding of non-Western musical repertoires and the field of computational musicology.
Abstract:
In this talk, we will explore our extensive research efforts in applying computational methodologies to analyze and understand diverse music traditions, with a focus on Carnatic music. We will delve into the journey from identifying research questions to disseminating impactful results, highlighting the collaborative process with musicians, scholars, and technologists within the Carnatic music community. This presentation will address various facets of our work, including the curation and creation of culturally rich datasets, the development of tailored signal processing and machine learning techniques, and the unique challenges we encountered in capturing the nuanced characteristics of Carnatic music. We will discuss specific tasks such as audio source separation and melodic analysis, showcasing the methodologies and tools designed to address the complex, ornamented structures of Carnatic music.
The talk will also cover evaluation frameworks that measure the relevance and accuracy of our findings, as well as the development of practical applications that support both academic research and broader community engagement. Finally, we will reflect on the broader implications of this research, considering its impact on the preservation and understanding of non-Western musical repertoires and the field of computational musicology.
มุมมอง: 35
วีดีโอ
Design, Development, and Deployment of Real-Time Drum Accompaniment Systems
มุมมอง 72วันที่ผ่านมา
PhD thesis defense of Behzad Haki December 4th, 2024 Abstract: This dissertation examines the generation of real-time symbolic drum accompaniments, with a particular focus on live improvisation contexts. While the research does occasionally focus on the audio domain, the majority of the research is centered on symbolic-to-symbolic systems. This dissertation addresses real-time drum accompanimen...
Embedded Machine Learning in Musical Instrument Design, by Chris Kiefer
มุมมอง 205วันที่ผ่านมา
Seminar at the MTG (UPF) - December 5th 2024 Embedded Machine Learning in Musical Instrument Design Chris Kiefer, University of Sussex Abstract: The 'Musically Embodied Machine Learning' project is currently running at University of Sussex, exploring the challenges and creative opportunities that arise when the processes of training and inference in machine learning are embedded within hybrid m...
David Toop and Sergi Jordà: open conversation on music and technology
มุมมอง 122หลายเดือนก่อน
The musician, writer, curator, and sound artist David Toop visited de MTG for an open conversation with Sergi Jordà about his work and vision of music with electronic media nowadays. UPF Campus Poblenou October 10th, 2024
Violin Performance Analysis using Weak Supervision
มุมมอง 1672 หลายเดือนก่อน
PhD thesis defense of Nazif Can Tamer October 2nd, 2024 Abstract: This thesis investigates the development of core Music Information Retrieval (MIR) technologies for Violin Performance Analysis, addressing both data and label scarcity. To mitigate data scarcity, the Violin Repertoire Dataset, a large-scale collection of pedagogically motivated repertoire, is introduced. To address label scarcit...
Deep Audio Representation Learning for Music Using Weak Supervision
มุมมอง 1192 หลายเดือนก่อน
PhD thesis defense of Pablo Alonso October 3rd, 2024 Abstract: Music audio tagging is the Music Information Retrieval task of assigning one or multiple labels to an audio signal. Music tagging systems are essential for developing applications involving cataloging, retrieval, or recommendation, so enhancing the accuracy, robustness, and efficiency of these models is beneficial for many real-worl...
High-Resolution Violin Transcription using Weak Labels
มุมมอง 1147 หลายเดือนก่อน
Presentation by Nazif Can Tamer at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). A descriptive transcription of a violin performance requires detecting not only the notes but also the fine-grained pitch variations, such as vibrato. Most existing deep learning methods for music transcription do not capture these variations and often need frame-level anno...
Sounds out of place? Score independent detection of conspicouous mistakes in piano performances.
มุมมอง 537 หลายเดือนก่อน
Presentation by Alia Morsi at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). In piano performance, some mistakes stand out to listeners, whereas others may go unnoticed. Former research concluded that the salience of mistakes depended on factors including their contextual appropriateness and a listener’s degree of familiarity to what is being performed. ...
TriAD: Capturing harmonics with 3D Convolutions
มุมมอง 777 หลายเดือนก่อน
Presentation by Miguel Pérez at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). Thanks to advancements in deep learning (DL), automatic music transcription (AMT) systems recently outperformed previous ones fully based on manual feature design. Many of these highly capable DL models, however, are computationally expensive. Researchers are moving towards sm...
TapTamDrum: A Dataset for Dualized Drum Patterns
มุมมอง 447 หลายเดือนก่อน
Presentation by Behzad Haki at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). Drummers spend extensive time practicing rudiments to develop technique, speed, coordination, and phrasing. These rudiments are often practiced on "silent" practice pads using only the hands. Additionally, many percussive instruments across cultures are played exclusively with ...
Efficient Supervised Training of Audio Transformers for Music Representation Learning
มุมมอง 877 หลายเดือนก่อน
Presentation by Pablo Alonso at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). In this work, we address music representation learning using convolution-free transformers. We build on top of existing spectrogram-based audio transformers such as AST and train our models on a supervised task using patchout training similar to PaSST. In contrast to previous ...
Leveraging pre-trained autoencoders for interpretable prototype learning of music audio
มุมมอง 677 หลายเดือนก่อน
Presentation by Pablo Alonso at ICASSP Workshop on Explainable AI for Speech and Audio (XAI-SA); 2024 Apr 15; Seoul, Korea. Abstract: We present PECMAE an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, we propose to decouple both training proc...
Critical art practices within Generative Music AI with Moisés Horta Valenzuela (𝔥𝔢𝔵𝔬𝔯𝔠𝔦𝔰𝔪𝔬𝔰)
มุมมอง 4807 หลายเดือนก่อน
Presentation, open discussion and demo by MMoisés Horta Valenzuela (𝔥𝔢𝔵𝔬𝔯𝔠𝔦𝔰𝔪𝔬𝔰). Conducted by Blazej Kotowski (MTG). AI is at a juncture where growing concerns about its ethical use span across all applications. In the field of generative AI in music, most ethical concerns are linked to its role in creative processes, the contentious practices in preparation of datasets, potential copyright in...
Cátedra IA y Música - Presentation
มุมมอง 9579 หลายเดือนก่อน
Presentation of the Cátedra UPF-BMAT en IA y Música / UPF-BMAT Chair on AI and Music. The UPF-BMAT Chair on Artificial Intelligence and Music is an initiative of the Music Technology Group (MTG), in collaboration with BMAT, a company specializing in music technology. The Chair is part of the National Artificial Intelligence Strategy (ENIA), co-funded by the Ministry of Economic Affairs and Digi...
Interpretable Deep-learning Models for Sound Event Detection and Classification
มุมมอง 240ปีที่แล้ว
PhD thesis defense of Pablo Zinemanas October 20th, 2023 Abstract: Deep-learning models have revolutionized state-of-the-art technologies in many research areas, but their black-box structure makes it difficult to understand their inner workings and the rationale behind their predictions. This may lead to unintended effects, such as being susceptible to adversarial attacks or the reinforcement ...
La IA y el ecosistema musical: desafíos, oportunidades y riesgos
มุมมอง 438ปีที่แล้ว
La IA y el ecosistema musical: desafíos, oportunidades y riesgos
Automatic Characterization and Generation of Music Loops and Samples for Electronic Music Production
มุมมอง 237ปีที่แล้ว
Automatic Characterization and Generation of Music Loops and Samples for Electronic Music Production
Music Technology Group - Universitat Pompeu Fabra
มุมมอง 128ปีที่แล้ว
Music Technology Group - Universitat Pompeu Fabra
Modeling Timbre for Neural Singing Synthesis
มุมมอง 5312 ปีที่แล้ว
Modeling Timbre for Neural Singing Synthesis
Exploration of Music Collections with Audio Embeddings
มุมมอง 3062 ปีที่แล้ว
Exploration of Music Collections with Audio Embeddings
Real-time music style classification with Essentia
มุมมอง 6652 ปีที่แล้ว
Real-time music style classification with Essentia
Real-time music auto-tagging in the browser with Essentia.js
มุมมอง 4812 ปีที่แล้ว
Real-time music auto-tagging in the browser with Essentia.js
Data-driven Pitch Content Description of Choral Singing Recordings
มุมมอง 2212 ปีที่แล้ว
Data-driven Pitch Content Description of Choral Singing Recordings
Continuing CompMusic: New approaches in the computational analysis of Carnatic Music
มุมมอง 2912 ปีที่แล้ว
Continuing CompMusic: New approaches in the computational analysis of Carnatic Music
Enhancing musicality: scientific, technological and practical challenges
มุมมอง 1962 ปีที่แล้ว
Enhancing musicality: scientific, technological and practical challenges
Audio Quality and Its Impact on Sound and Music Processing
มุมมอง 5422 ปีที่แล้ว
Audio Quality and Its Impact on Sound and Music Processing
Training Sound Event Classifiers Using Different Types of Supervision
มุมมอง 5603 ปีที่แล้ว
Training Sound Event Classifiers Using Different Types of Supervision
Music Recommender Systems: Taking Into Account The Artists' Perspective
มุมมอง 3463 ปีที่แล้ว
Music Recommender Systems: Taking Into Account The Artists' Perspective