Luis Gustavo Martins
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Luis Gustavo Martins has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
George Tzanetakis
University of Victoria, Victoria, BC, Canada
3 shared publications- George Tzanetakis
University of Victoria
3 shared publications Mathieu Lagrange
IRCAM CNRS, 1, place Igor Stravinsky, 75004 Paris, France
3 shared publications- Luis Filipe Teixeira
INESC TEC
2 shared publications - Mathieu Lagrange
Dept. of Comput. Sci., Univ. of Victoria, Canada
2 shared publications - André Baltazar
André Baltazar, Universidade Católica Portuguesa, School of Arts, Research Centre for Science and Technology of the Arts, Rua Diogo Botelho 1327, 4169-005 Porto, Portugal.. Website: https://ciencia.ucp.pt/pt/persons/andr%C3%A9-baltazar
1 shared publication
Latest Publications
- 1 January 2015
- Published by IGI Global Scientific Publishing
- p. 224-254
ZatLab
Computer programming is not an easy task, and as with all difficult tasks, it can be faced as tedious, impossible to do, or as a challenge. Therefore, learning to program with a purpose enables that “challenge mindset” and encourages the student to apply himself in overcoming his handicaps and exploring different theories and methods to achieve his goal. This chapter describes the process of programming a framework with the purpose of achieving real time human gesture recognition. Just this is already a good challenge, but the ultimate goal is to enable new ways of Human-Computer Interaction through expressive gestures and to allow a performer the possibility of controlling (with his gestures), in real time, creative artistic events. The chapter starts with a review on human gesture recognition. Then it presents the framework architecture, its main modules, and algorithms. It closes with the description of two artistic applications using the ZatLab framework.
- 1 January 2015
- Published by IGI Global Scientific Publishing
- p. 224-254
ZatLab
Computer programming is not an easy task, and as with all difficult tasks, it can be faced as tedious, impossible to do, or as a challenge. Therefore, learning to program with a purpose enables that “challenge mindset” and encourages the student to apply himself in overcoming his handicaps and exploring different theories and methods to achieve his goal. This chapter describes the process of programming a framework with the purpose of achieving real time human gesture recognition. Just this is already a good challenge, but the ultimate goal is to enable new ways of Human-Computer Interaction through expressive gestures and to allow a performer the possibility of controlling (with his gestures), in real time, creative artistic events. The chapter starts with a review on human gesture recognition. Then it presents the framework architecture, its main modules, and algorithms. It closes with the description of two artistic applications using the ZatLab framework.
- 1 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 237-238
NIME Education at the School of Arts of the Portuguese Catholic University/CITAR
The liberalization of radio and television broadcast industry in Portugal and the recent flow of investment into the field of creative industries, together with exponential developments in communication technologies, resulted in a growing demand for professionals in the field of audiovisual production. The new Media Industry requires qualified human resources with strong skills in Artist, Technology, Culture and Ethics. This paper presents some of the courses currently offered at the EA-UCP that have some degree of relevancy to NIME (New Interfaces for Musical Expression). Different professors, with different backgrounds (from arts and music to engineering), are responsible for each one the courses, and some of the courses have in fact more than one professor, usually with different backgrounds, allowing to cover the different facets of more interdisciplinar curricular units.
- 1 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 237-238
NIME Education at the School of Arts of the Portuguese Catholic University/CITAR
The liberalization of radio and television broadcast industry in Portugal and the recent flow of investment into the field of creative industries, together with exponential developments in communication technologies, resulted in a growing demand for professionals in the field of audiovisual production. The new Media Industry requires qualified human resources with strong skills in Artist, Technology, Culture and Ethics. This paper presents some of the courses currently offered at the EA-UCP that have some degree of relevancy to NIME (New Interfaces for Musical Expression). Different professors, with different backgrounds (from arts and music to engineering), are responsible for each one the courses, and some of the courses have in fact more than one professor, usually with different backgrounds, allowing to cover the different facets of more interdisciplinar curricular units.
- 1 September 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 619-622
The development of an interactive virtual scenography for the opera A Menina da Gotinha De Água
This paper describes the development of the virtual scenography for the opera for choir, narrator and live electronics A Menina da Gotinha de Água. The objective of the virtual scenography was to substitute the traditional illumination and scenography systems with projections and also introduce an interactive aspect for the visual elements of the stage. The final visual result was a composition of pre-edited videos, real-time interactive animations and pre-made children drawings that were made interactive. The interaction was divided in two parts: a master controller software with graphical user interface and two Reactables (Reactable Live!)[1] with custom software, through which, a master operator and six children could control images and real-time effects. We conclude that the dialogue between the music, choreography and scenography was enhanced by the use of an interactive virtual scenography. Designing the live visuals to highlight each key moment of the musical and literal text increased the general understanding and appreciation of the opera by the public.
- 1 September 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 619-622
The development of an interactive virtual scenography for the opera A Menina da Gotinha De Água
This paper describes the development of the virtual scenography for the opera for choir, narrator and live electronics A Menina da Gotinha de Água. The objective of the virtual scenography was to substitute the traditional illumination and scenography systems with projections and also introduce an interactive aspect for the visual elements of the stage. The final visual result was a composition of pre-edited videos, real-time interactive animations and pre-made children drawings that were made interactive. The interaction was divided in two parts: a master controller software with graphical user interface and two Reactables (Reactable Live!)[1] with custom software, through which, a master operator and six children could control images and real-time effects. We conclude that the dialogue between the music, choreography and scenography was enhanced by the use of an interactive virtual scenography. Designing the live visuals to highlight each key moment of the musical and literal text increased the general understanding and appreciation of the opera by the public.
- 1 March 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1969-1972
Cluster aware normalization for enhancing audio similarity
An important task in Music Information Retrieval is content-based similarity retrieval in which given a query music track, a set of tracks that are similar in terms of musical content are retrieved. A variety of audio features that attempt to model different aspects of the music have been proposed. In most cases the resulting audio feature vector used to represent each music track is high dimensional. It has been observed that high dimensional music similarity spaces exhibit some anomalies: hubs which are tracks that are similar to many other tracks, and orphans which are tracks that are not similar to most other tracks. These anomalies are an artifact of the high dimensional representation rather than actually based on the musical content. In this work we describe a distance normalization method that is shown to reduce the number of hubs and orphans. It is based on post-processing the similarity matrix that encodes the pair-wise track similarities and utilizes clustering to adapt the distance normalization to the local structure of the feature space.
- 1 March 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1969-1972
Cluster aware normalization for enhancing audio similarity
An important task in Music Information Retrieval is content-based similarity retrieval in which given a query music track, a set of tracks that are similar in terms of musical content are retrieved. A variety of audio features that attempt to model different aspects of the music have been proposed. In most cases the resulting audio feature vector used to represent each music track is high dimensional. It has been observed that high dimensional music similarity spaces exhibit some anomalies: hubs which are tracks that are similar to many other tracks, and orphans which are tracks that are not similar to most other tracks. These anomalies are an artifact of the high dimensional representation rather than actually based on the musical content. In this work we describe a distance normalization method that is shown to reduce the number of hubs and orphans. It is based on post-processing the similarity matrix that encodes the pair-wise track similarities and utilizes clustering to adapt the distance normalization to the local structure of the feature space.
- Open Access
- 19 October 2009
- Published by Association for Computing Machinery (ACM)
- p. 705-708
Improving automatic music tag annotation using stacked generalization of probabilistic SVM outputs
- 19 October 2009
- Published by Association for Computing Machinery (ACM)
- p. 705-708
Open AccessImproving automatic music tag annotation using stacked generalization of probabilistic SVM outputs
- Open Access
- 5 May 2009
- Published by Universidade Catolica Portuguesa in Journal of Science and Technology of the Arts
- Vol. 1 (1)
Artech 2008
- 5 May 2009
- Published by Universidade Catolica Portuguesa in Journal of Science and Technology of the Arts
- Vol. 1 (1)
Open AccessArtech 2008
- 26 October 2008
- Published by Association for Computing Machinery (ACM)
- p. 873-876
Open AccessMarsyasX
- 1 March 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 165-168
A Computationally Efficient Scheme for Dominant Harmonic Source Separation
The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an harmonicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic computational auditory scene analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.
- 1 March 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 165-168
A Computationally Efficient Scheme for Dominant Harmonic Source Separation
The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an harmonicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic computational auditory scene analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.
- 1 November 2007
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 122 (5_Suppleme) , 2988-2989
A framework for sound source separation using spectral clustering
Clustering based on the normalized cut criterion, and more generally, spectralclustering methods, are techniques originally proposed to model perceptual grouping tasks, such as image segmentation in computer vision. In this work, it is shown how such techniques can be applied to the problem of dominant melodic source separation in polyphonic music audio signals. One of the main advantages of this approach is the ability to incorporate mutiple perceptually‐inspired grouping criteria into a single framework without requiring multiple processing stages, as many existing computational auditory science analysis approaches do. Experimental results for several tasks, including dominant melodypitch detection, are presented. The system is based on a sinusoidal modeling analysis front‐end. A novel similarity cue based on harmonicity (harmonically‐wrapped peak similariy) is also introduced. The proposed system is data‐driven (i.e., requires no prior knowledge about the extracted source), causal, robust, practical, and efficient (close to real‐time on a fast computer). Although a specific implementation is presented, one of the main advantages of the proposed approach is its ability to utilize different analysis front‐ends and grouping criteria in a straightforward manner.
- 1 November 2007
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 122 (5_Suppleme) , 2988-2989
A framework for sound source separation using spectral clustering
Clustering based on the normalized cut criterion, and more generally, spectralclustering methods, are techniques originally proposed to model perceptual grouping tasks, such as image segmentation in computer vision. In this work, it is shown how such techniques can be applied to the problem of dominant melodic source separation in polyphonic music audio signals. One of the main advantages of this approach is the ability to incorporate mutiple perceptually‐inspired grouping criteria into a single framework without requiring multiple processing stages, as many existing computational auditory science analysis approaches do. Experimental results for several tasks, including dominant melodypitch detection, are presented. The system is based on a sinusoidal modeling analysis front‐end. A novel similarity cue based on harmonicity (harmonically‐wrapped peak similariy) is also introduced. The proposed system is data‐driven (i.e., requires no prior knowledge about the extracted source), causal, robust, practical, and efficient (close to real‐time on a fast computer). Although a specific implementation is presented, one of the main advantages of the proposed approach is its ability to utilize different analysis front‐ends and grouping criteria in a straightforward manner.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19493983,p. 219-226
Speaker Segmentation of Interviews Using Integrated Video and Audio Change Detectors
In this paper, we study the use of audio and visual cues to perform speaker segmentation of audiovisual recordings of formal meetings such as interviews, lectures, or courtroom sessions. The sole use of audio cues for such recordings can be ineffective due to low recording quality and high level of background noise. We propose to use additional cues from the video stream by exploiting the relative static locations of speakers among the scene. The experiments show that the combination of those multiple cues helps to identify more robustly the transitions among speakers.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19493983,p. 219-226
Speaker Segmentation of Interviews Using Integrated Video and Audio Change Detectors
In this paper, we study the use of audio and visual cues to perform speaker segmentation of audiovisual recordings of formal meetings such as interviews, lectures, or courtroom sessions. The sole use of audio cues for such recordings can be ineffective due to low recording quality and high level of background noise. We propose to use additional cues from the video stream by exploiting the relative static locations of speakers among the scene. The experiments show that the combination of those multiple cues helps to identify more robustly the transitions among speakers.