menu

School of Electronic Engineering and Computer Science

People menu

Dr George Fazekas

George

Lecturer in Digital Media

Email: g.fazekas@qmul.ac.uk
Telephone: +44 20 7882 8024
Room Number: Peter Landin, CS 414
Website: http://www.eecs.qmul.ac.uk/~gyorgyf/

Teaching

Introduction to Digital Audio (Undergraduate)

This module covers the entire field of digital audio, including some depth in the subfields and related subjects. It is concerned with the creation, representation, modification and evaluation of digital audio. It introduces the basics of sound, and the key concepts of acoustics that are required to understand how sound is created, represented, transmitted and perceived. The important characteristics of sound are described, such as the intensity, frequency, pitch and timbre. It gives students the knowledge to understand how sound may be accurately represented digitally. Different representations, such as wav, midi and mp3 are introduced. The students are also taught critical listening skills, including the ability to properly create, record and discern sounds, identify subtle problems, identify frequencies, and hear hidden distortions.

Research Methods I (Postgraduate)

The module will teach the generic high-level research and transferable skills applicable to pure and applied research in computer science. It will also prepare students for employment or further academic study by enabling them to apply these in relevant, practical contexts.

The Semantic Web (Undergraduate/Postgraduate)

The idea of putting semantic information on the Web has been around for a long time: we now have the beginnings of a practical application. This has its foundations in what is called Description Logic, which strikes a good balance between tractability and usability. This has led to a Web language called OWL, which is at the centre of modern work on the Semantic Web: there are now useful implementations, and there are workable, if modest, applications of this technology.

Research

Research Interests:

My main research interest is Semantic Audio, an interdisciplinary field in the confluence of Digital Signal Processing, Machine Learning, and various knowledge representation and knowledge sharing technologies such as Semantic Web Ontologies, Linked-data, knowledge-based reasoning and the Semantic Web. I'm interested in extracting, analysing and linking data about music and developing applications that use semantic metadata, bringing the power of semantic technologies to music technology.

Publications

  • Choi K, Fazekas G, Sandler M et al. (2018). The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging. nameOfConference
  • CHOI K, FAZEKAS G, SANDLER M et al. (2017). Transfer learning for music classification and regression tasks. The 18th International Society of Music Information Retrieval (ISMIR) Conference
  • Bechhofer S, Page K, Weigl D et al. (2017). Linked Data Publication of Live Music Archives and Analyses. 16th International Semantic Web Conference
  • Liang B, Fazekas G, SANDLER M (2017). Detection of Piano Pedaling Techniques on the Sustain Pedal. The 143rd Convention of the Audio Engineering Society
  • Marengo L, FAZEKAS G, TOMBROS A (2017). The Interaction of Casual Users with Digital Collections of Visual Art: An Exploratory Study of the WikiArt Website. 19th International Conference on Human-Computer Interaction (HCI’17)
  • Liang B, Fazekas G, McPherson A et al. (2017). Piano Pedaller: A Measurement System for Classification and Visualisation of Piano Pedalling Techniques. New Interfaces for Musical Expression
  • Choi K, Fazekas G, Cho K et al. (2017). A Tutorial on Deep Learning for Music Information Retrieval. nameOfConference
  • Sheng D, Fazekas G (2017). Automatic Control Of The Dynamic Range Compressor Using A Regression Model And A Reference Sound. nameOfConference
  • Wilmering T, Thalmann F, Fazekas G et al. (2017). Bridging Fan Communities and Facilitating Access to Music Archives through Semantic Audio Applications. nameOfConference
  • Pauwels J, O hanlon K, Fazekas G et al. (2017). Confidence Measures and Their Applications in Music Labelling Systems Based on Hidden Markov Models. nameOfConference
  • Choi K, Fazekas G, Sandler M et al. (2017). Convolutional Recurrent Neural Networks for Music Classification. nameOfConference
  • Liang B, Fazekas G, Sandler M (2017). Discovering Feature Relevance in Pedalling Analyses of Piano Music. nameOfConference
  • Sheng D, Fazekas G (2017). Feature design for intelligent control of the dynamic range compressor using audio decomposition. nameOfConference
  • Fazekas G, Barthet M, Stockman TE (2017). Proceedings of the 12th International Audio Mostly Conference on Augmented and Participatory Sound and Music Experiences, London, United Kingdom, August 23 - 26, 2017.. nameOfConference
  • Page K, Bechhofer S, Fazekas G et al. (2017). Realising a Layered Digital Library: Exploration and Analysis of the Live Music Archive through Linked Data. nameOfConference
  • Liang B, Fazekas G, Sandler M (2017). Recognition of Piano Pedalling Techniques Using Gesture Data. nameOfConference
  • Choi K, Fazekas G, Sandler M et al. (2017). Transfer learning for music classification and regression tasks [best paper award]. nameOfConference
  • LIANG B, fazekas G, mcpherson A et al. (2016). Classification of Piano Pedaling Techniques Using Gesture Data from a Non-Intrusive Measurement System. DMRN+11: Digital Music Research Network One-day Workshop 2016
  • Juric D, FAZEKAS G (2016). Knowledge extraction from audio content service providers’ API descriptions. Metadata and Semantics Research (MTSR)
  • Mora-Mcginity M, Allik A, FAZEKAS G et al. (2016). MusicWeb: Music discovery with open linked semantic metadata. Metadata and Semantics Research (MTSR)
  • Wilmering T, FAZEKAS G, Sandler M (2016). AUFX-O: Novel methods for the representation of audio processing workflows. 15th International Semantic Web Conference
  • Allik A M, Fazekas G SM (2016). Musicweb: Music Discovery with Open Linked Semantic Metadata [Nominee, Best Demo Award]. nameOfConference
  • ALLIK A, FAZEKAS G, SANDLER M (2016). Ontological representation of audio features. 15th International Semantic Web Conference
  • CHOI K, sandler M, fazekas G (2016). Text-based LSTM networks for Automatic Music Composition. Conference on Computer Simulation of Musical Creativity
  • Saari P, FAZEKAS G, Eerola T et al. (2016). Genre-adaptive Semantic Computing Enhances Audio-based Music Mood Prediction. nameOfConference
  • Buccoli M, Zanoni M, Fazekas G et al. (2016). A Higher-Dimensional Expansion of Affective Norms for English Terms for Music Tagging. nameOfConference
  • Allik A, Fazekas G, Sandler M (2016). An Ontology for Audio Features. nameOfConference
  • Font F, Brookes T, Fazekas G et al. (2016). Audio Commons: Bringing Creative Commons Audio Content to the Creative Industries. nameOfConference
  • Choi K, Fazekas G, Sandler M (2016). Automatic Tagging Using Deep Convolutional Neural Networks. nameOfConference
  • Thalmann F, Fazekas G, Wiggins GA et al. (2016). Creating, Visualizing, and Analyzing Dynamic Music Objects in the Browser with the Dymo Designer. nameOfConference
  • Barthet M, Fazekas G, Thalmann F et al. (2016). Crossroads: Interactive Music Systems Transforming Performance, Production and Listening. nameOfConference
  • Barthet M, Fazekas G, Allik A et al. (2016). From interactive to adaptive mood-based music listening experiences in social or personal context. nameOfConference
  • Carrillo A, Thalmann F, Fazekas G et al. (2016). Geolocation Adaptive Music Player. nameOfConference
  • Chiliguano P, Fazekas G (2016). Hybrid music recommender using content-based and social information. nameOfConference
  • Mora-McGinity M, Allik A, Fazekas G et al. (2016). MusicWeb: Music discovery with open linked semantic metadata. nameOfConference
  • Stables R, De Man B, Enderby S et al. (2016). Semantic description of timbral transformations in music production. nameOfConference
  • Thalmann F, Carrillo G, Wiggins GA et al. (2016). The Mobile Audio Ontology: Experiencing Dynamic Music Objects on Mobile Devices. nameOfConference
  • Thalmann F, Perez Carillo A, Fazekas G et al. (2016). The Semantic Music Player: A Smart Mobile Player Based on Ontological Structures and Analytical Feature Metadata. nameOfConference
  • Choi K, Fazekas G, Sandler M (2016). Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions. nameOfConference
  • Allik A, Fazekas G, Barthet M et al. (2016). myMoodplay: An interactive mood-based music discovery app. nameOfConference
  • CHOI K, Fazekas G, sandler MARK et al. (2015). Auralisation of Deep Convolutional Neural Networks: Listening to Learned Features. International Society for Music Information Retrieval Conference
  • Wilmering T, Fazekas G, Allik A et al. (2015). Audio effects data on the semantic web. nameOfConference
  • Wilmering T, Fazekas G, Dixon S et al. (2015). Automating Annotation of Media with Linked Data Workflows. nameOfConference
  • Mauch M, Cannam C, Bittner R et al. (2015). Computer-aided Melody Note Transcription Using the Tony Software: Accuracy and Efficiency. nameOfConference
  • FAZEKAS G (2015). Convergence of technologies to connect audio with meaning: from Semantic Web ontologies to semantic audio production. nameOfConference
  • Barthet M, Fazekas G, Allik A et al. (2015). Moodplay: an interactive mood-based musical experience. nameOfConference
  • Thalmann F, Carrillo A, Fazekas G et al. (2015). Navigating Ontological Structures based on Feature Metadata Using the Semantic Music Player. nameOfConference
  • Tian M, Fazekas G, Black DAA et al. (2015). ON THE USE OF THE TEMPOGRAM TO DESCRIBE AUDIO CONTENT AND ITS APPLICATION TO MUSIC STRUCTURAL SEGMENTATION. nameOfConference
  • Tian M, Fazekas G, Black DAA et al. (2015). On the Use of the Tempogram to Describe Audio Content and its Application to Music Structural Segmentation. nameOfConference
  • Liang B, Fazekas G, Sandler M (2015). The Organ Web App. nameOfConference
  • Wilmering T, Fazekas G, Dixon S et al. (2015). Towards High Level Feature Extraction from Large Live Music Recording Archives. nameOfConference
  • Zanoni M, Setragno F, Antonacci F et al. (2015). Training-based Semantic Descriptors modeling for violin quality sound characterization. nameOfConference
  • Choi K, Fazekas G, Sandler M (2015). Understanding Music Playlists. nameOfConference
  • Fazekas G, BARTHET M, Sandler MB (2014). Novel Methods in Facilitating Audience and Performer Interaction Using the Mood Conductor Framework. nameOfConference
  • Kolozali S, Fazekas G, Barthet M et al. (2014). A framework for automatic ontology generation based on semantic audio analysis. nameOfConference
  • Fazekas G, Kudumakis P (2014). A second screen music discovery and recommendation service based on social and cultural factors. nameOfConference
  • Bechhofer S, Dixon S, Fazekas G et al. (2014). Computational Analysis of the Live Music Archive. nameOfConference
  • Mora-McGinity M, Fazekas G, Ogilive G (2014). Creating Semantic Links between Research Articles and Music Artists. nameOfConference
  • Tian M, Fazekas G, Black DAA et al. (2014). Design and Evaluation of Onset Detectors Using Different Fusion Policies. nameOfConference
  • Mauch M, Cannam C, Fazekas G (2014). Efficient computer-aided pitch track and note estimation for scientific applications. nameOfConference
  • Lou T, Barthet M, Fazekas G et al. (2014). Evaluation and Improvement of the Mood Conductor Interactive System. nameOfConference
  • Font F, Oramas S, Fazekas G et al. (2014). Extending Tagging Ontologies with Domain Specific Knowledge. nameOfConference
  • FAZEKAS G, Barthet M, Sandler M (2014). Novel Methods in Facilitating Audience and Performer Interaction using the Mood Conductor Framework. nameOfConference
  • Stables R, Enderby S, De Man B et al. (2014). SAFE: A System for Extraction and Retrieval of Semantic Audio Descriptors. nameOfConference
  • Baume C, Fazekas G, Barthet M et al. (2014). Selection of audio features for music emotion recognition using production music. nameOfConference
  • Mora-McGinity M, Ogilvie G, Fazekas G (2014). Semantically Linking Humanities Research Articles and Music Artists. nameOfConference
  • De Man B, Mora-Mcginity M, Fazekas G et al. (2014). The Open Multitrack Testbed. nameOfConference
  • Stables R, Enderby S, De Man B et al. (2014). The SAFE project: Musical semantics in the DAW. nameOfConference
  • Kolozali S, Barthet M, Fazekas G et al. (2013). Automatic Ontology Generation for Musical Instruments Based on Audio Analysis. nameOfConference
  • Fazekas G, Barthet M, Sandler M (2013). The BBC Desktop Jukebox music recommendation system: A large-scale trial with professional users. IEEE International Conference on Multimedia and Expo
  • Allik A, Fazekas G, Dixon S et al. (2013). A Shared Vocabulary for Audio Features. nameOfConference
  • Kosta K, Song Y, Fazekas G et al. (2013). A Study of Cultural Dependence of Perceived Mood in Greek Music. nameOfConference
  • Wilmering T, Fazekas G, Sandler M (2013). Audio Effect Classification Based on Auditory Perceptual Attributes. nameOfConference
  • Tian M, Black DAA, Fazekas G et al. (2013). Content-based Emotion Categorisation Analysis of Chinese Cultural Revolution Songs. nameOfConference
  • Fazekas G, Sandler MB, IEEE (2013). DESCRIBING AUDIO PRODUCTION WORKFLOWS ON THE SEMANTIC WEB. nameOfConference
  • Barthet M, Marston D, Baume C et al. (2013). Design and Evaluation of Semantic Mood Models for Music Recommendation Using Editorial Tags. nameOfConference
  • Lou T, Barthet M, Fazekas G et al. (2013). Evaluation of the Mood Conductor Interactive System Based on Audience and Performers’ Perspectives. nameOfConference
  • Allik A, Fazekas G, Dixon S et al. (2013). Facilitating Music Information Research with Shared Open Vocabularies. nameOfConference
  • Fazekas G, Barthet M, Sandler MB et al. (2013). Mood Conductor: Emotion-Driven Interactive Music Performance. nameOfConference
  • Barthet M, FAZEKAS G, Sandler M (2013). Music Emotion Recognition: From Content- to Context-Based Models. nameOfConference
  • Wilmering T, Fazekas G, Sandler M (2013). Semantic Metadata for Music Production Projects. nameOfConference
  • Saari P, Barthet M, Fazekas G et al. (2013). Semantic models of musical mood: Comparison between crowd-sourced and curated editorial tags. nameOfConference
  • Wilmering T, Fazekas G, Sandler M (2013). The Audio Effects Ontology. nameOfConference
  • Fazekas G, Barthet M, Sandler M (2013). The Mood Conductor System: Audience and Performer Interaction using Mobile Technology and Emotion Cues. nameOfConference
  • Saari P, Eerola T, Fazekas G et al. (2013). The Role of Audio and Tags in Music Mood Prediction: a Study Using Semantic Layer Projection. nameOfConference
  • Tian M, Fazekas G, Black DAA et al. (2013). Towards the Representation of Chinese Traditional Music: A State of the Art Review of Music Metadata Standards. nameOfConference
  • Saari P, Eerola T, Fazekas G et al. (2013). Using Semantic Layer Projection for Enhancing Music Mood Prediction With Audio Features. nameOfConference
  • Song Y, Dixon S, Pearce M et al. (2013). Using Tags to Select Stimuli in the Study of Music and Emotion. nameOfConference
  • Wilmering T, Fazekas G, Sandler M (2012). High level semantic metadata for the control of multitrack adaptive audio effects. nameOfConference
  • Fazekas G, Sandler M (2012). Knowledge Representation Issues in Audio-Related Metadata Model Design. nameOfConference
  • Terrell MJ, Fazekas G, Simpson AJR et al. (2012). Listening level changes music similarity. nameOfConference
  • Barthet M, Fazekas G, Sandler M (2012). Multidisciplinary Perspectives on Music Emotion Recognition: Implications for Content and Context-Based Models. nameOfConference
  • Fazekas G, Wilmering T (2012). Semantic Web and Semantic Audio Technologies. nameOfConference
  • Fazekas G, Ewert S, Allik A et al. (2012). Shared Open Vocabularies and Semantic Media. nameOfConference
  • Barthet M, Fazekas G, Dixon S et al. (2012). Social Media Retrieval for Music Education. nameOfConference
  • Rumsey F, Schulein B, Herre J et al. (2012). Technology Trends in Auto Engineering A report by the AES Technical Council. nameOfConference
  • Fazekas G, Sandler MB (2011). The studio ontology framework. nameOfConference
  • Wilmering T, Fazekas G, Sandler MB (2011). Towards ontological representations of digital audio effects. nameOfConference
  • Fazekas G, Wilmering T, Sandler MB (2011). A knowledge representation framework for context-dependent audio processing. nameOfConference
  • Kolozali S, Fazekas G, Barthet M et al. (2011). Knowledge representation issues in musical instrument ontology design. nameOfConference
  • Barthet M, Anglade A, Fazekas G et al. (2011). Music recommendation for music learning: Hotttabs a multimedia guitar tutor. nameOfConference
  • Tidhar D, Fazekas G, Mauch M et al. (2011). Tempest - harpsichord temperament estimation in a Semantic Web environment. nameOfConference
  • Fazekas G, Sandler M (2011). The Studio Ontology Framework. nameOfConference
  • Wilmering T, Fazekas G, Sandler MB (2011). Towards ontological representations of digital audio effects. nameOfConference
  • Kolozali S, Barthet M, Fazekas G et al. (2011). Towards the automatic generation of a Semantic Web ontology for musical instruments. nameOfConference
  • Fazekas G, Raimond Y, Jacobson K et al. (2010). An Overview of Semantic Web Activities in the OMRAS2 Project. nameOfConference
  • Fazekas G, Tidhar D (2010). TempEst - Temperament estimation Web service. nameOfConference
  • Tidhar D, Fazekas G, Mauch M et al. (2010). Temperament Estimation as an MIR task. nameOfConference
  • Wilmering T, Fazekas G, Sandler M (2010). The effects of reverberation on onset detection tasks. nameOfConference
  • Raimond Y, Gängler T, Giasson F et al. (2010). The music ontology specification. nameOfConference
  • Kolozali S, Barthet M, Fazekas G et al. (2010). The musical instrument ontology. nameOfConference
  • Kolozali S, Barthet M, Fazekas G et al. (2010). Towards the automatic generation of a Semantic Web ontology for musical instruments. nameOfConference
  • Cannam C, Fazekas G, Noland K (2009). A Demonstration of Sonic Visualiser. nameOfConference
  • Fazekas G, Cannam C, Sandler M (2009). A Simple Guide to Automated Music Analysis on the Semantic Web (white paper). nameOfConference
  • Fazekas G, Sandler M (2009). Novel methods in information management for advanced audio workflows. nameOfConference
  • Fazekas G, Sandler M (2009). Ontology based information management in music production. nameOfConference
  • Tidhar D, Fazekas G, Kolozali S et al. (2009). Publishing Music Similarity Features on the Semantic Web. nameOfConference
  • Fazekas G, Cannam C, Sandler M (2009). Reusable metadata and software components for automatic audio analysis. nameOfConference
  • Fazekas G, Sandler M (2009). Uncovering the details of music production using ontologies. nameOfConference
  • Fazekas G, Raimond Y, Sandler M (2008). A framework for producing rich musical metadata in creative music production. nameOfConference
  • Fazekas G, Sandler M (2008). Ontology based information management in music production. nameOfConference
  • Fazekas G, Sandler M (2007). Intelligent editing of studio recordings with the help of automatic music structure extraction. nameOfConference
  • Fazekas G, Sandler M (2007). Structural decomposition of recorded vocal performances and its application to intelligent audio editing. nameOfConference
Return to top