An approach to predicting bowing control parameter contours in violin performance

We present a machine learning approach to modeling bowing control parametercontours in violin performance. Using accurate sensing techniqueswe obtain relevant timbre-related bowing control parameters such as bowtransversal velocity, bow pressing force, and bow-bridge distance of eachperformed note. Each performed note is represented by a curve parametervector and a number of note classes are defined. The principal componentsof the data represented by the set of curve parameter vectors are obtainedfor each class. Once curve parameter vectors are expressed in the new spacedefined by the principal components, we train a model based on inductivelogic programming, able to predict curve parameter vectors used for renderingbowing controls. We evaluate the prediction results and show the potentialof the model by predicting bowing control parameter contours from anannotated input score.

Statistical modeling of violin bowing parameter contours

We present a framework for modeling right-hand gestures in bowed-string instrument playing, applied to violin. Nearly non-intrusive sensing techniques allow for accurate acquisition of relevant timbre-related bowing gesture parameter cues. We model the temporal contour of bow transversal velocity, bow pressing force, and bow-bridge distance as sequences of short segments, in particular B´ezier cubic curve segments. Considering different articulations, dynamics, andcontexts, a number of note classes is defined. Gesture parameter contours of a performance database are analyzed at note-level by following a predefined grammar that dictatescharacteristics of curve segment sequences for each of the classes into consideration. Based on dynamic programming, gesture parameter contour analysis provides an optimal curve parameter vector for each note. The informationpresent in such parameter vector is enough for reconstructing original gesture parameter contours with significant fidelity. From the resulting representation vectors, weconstruct a statistical model based on Gaussian mixtures, suitable for both analysis and synthesis of bowing gesture parameter contours. We show the potential of the modelby synthesizing bowing gesture parameter contours from an annotated input score. Finally, we point out promising applicationsand developments.

Classification of indian classical vocal styles from melodic contours

A prominent categorization of Indian classical music is the Hindustani and Carnatic traditions, the two styleshaving evolved under distinctly different historical andcultural influences. Both styles are grounded in the melodicand rhythmic framework of raga and tala. The styles differ along dimensions such as instrumentation,aesthetics and voice production. In particular, Carnatic music is perceived as being more ornamented. The hypothesisthat style distinctions are embedded in the melodic contour is validated via subjective classification tests. Melodic features representing the distinctive characteristicsare extracted from the audio. Previous work based on the extent of stable pitch regions is supported by measurements of musicians’ annotations of stable notes. Further, a new feature is introduced that captures thepresence of specific pitch modulations characteristic ofornamentation in Indian classical music. The combined features show high classification accuracy on a database of vocal music of prominent artistes. The misclassifications are seen to match actual listener confusions.

A new approach to segmentation based on fusing circumscribed contours, region growing and clustering

One of the major problems in machine vision is the segmentation of images of natural scenes. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. The main contours of the scene are detected and used to guide the posterior region growing process. The algorithm places a number of seeds at both sides of a contour allowing stating a set of concurrent growing processes. A previous analysis of the seeds permits to adjust the homogeneity criterion to the regions's characteristics. A new homogeneity criterion based on clustering analysis and convex hull construction is proposed

A concurrent region growing algorithm guided by circumscribed contours

Image segmentation of natural scenes constitutes a major problem in machine vision. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. This approach begins by detecting the main contours of the scene which are later used to guide a concurrent set of growing processes. A previous analysis of the seed pixels permits adjustment of the homogeneity criterion to the region's characteristics during the growing process. Since the high variability of regions representing outdoor scenes makes the classical homogeneity criteria useless, a new homogeneity criterion based on clustering analysis and convex hull construction is proposed. Experimental results have proven the reliability of the proposed approach

Detector de contorns basat en el domini transformat

RESUM En aquest document es presenta un detector de contorns d’imatges basat en el domini transformat. A partir de la interpretació de la transformada de Fourier de la imatge i la seva formulació matricial en termes dels diferents modes, es realitza una selecció de les components passa baixes a partir de les quals es reconstrueix la component de baixa freqüència que es resta de la imatge original per tal d’obtenir el detector. Aquest detector de contorns no és esbiaixat. L’algorisme pot ser aplicat utilitzant diferents mides del bloc de processament, que pot anar de la imatge sencera a blocs de reduïdes dimensions: 36X36, 16x16 o 8x8, per fer un seguiment de les propietats locals de la imatge quan aquesta és presenta característiques espacials poc uniformes.

A method to obtain the integrated contour image in colour scenes

This paper describes a method to achieve the most relevant contours of an image. The presented method proposes to integrate the information of the local contours from chromatic components such as H, S and I, taking into account the criteria of coherence of the local contour orientation values obtained from each of these components. The process is based on parametrizing pixel by pixel the local contours (magnitude and orientation values) from the H, S and I images. This process is carried out individually for each chromatic component. If the criterion of dispersion of the obtained orientation values is high, this chromatic component will lose relevance. A final processing integrates the extracted contours of the three chromatic components, generating the so-called integrated contours image

L'adquisició de l'entonació en català, castellà i anglès

El principal objectiu del projecte és analitzar el desenvolupament de l’entonació de tres llengües, el català, el castellà i l’anglès. Pretenem investigar el desenvolupament dels diferents patrons entonatius que trobem en la producció primerenca, avaluant si, efectivament, aquests primers contorns produïts pels nens reflecteixen o no les propietats prosòdiques específiques de la llengua input dels adults. En resum, l'objectiu és poder esbrinar com l'infant va configurant la seva gramàtica entonativa així com el significat que va associat a aquestes produccions entonatives. Pretenem analitzar dos tipus de dades. Per una banda, un corpus d’entonació que conté els diàlegs controlats entre 36 nens i 36 adults (12 nens de cada llengua de 2, 4 i 6 anys) i que permet de comparar les mateixes frases produïdes pels adults i pels nens. Per altra banda, els corpus longitudinals de CHILDES que ens permeten analitzar dades sobre actes de parla i formes entonatives (corpus Serra-Solé per al català, corpus Ornat i Llinàs-Ojea per al castellà i el corpus Providence per a l'anglès americà i el Forrester per a l'anglès britànic).

Regions of rationality: Maps for bounded agents

An important problem in descriptive and prescriptive research in decision making is to identify regions of rationality, i.e., the areas for which heuristics are and are not effective. To map the contours of such regions, we derive probabilities that heuristics identify the best of m alternatives (m > 2) characterized by k attributes or cues (k > 1). The heuristics include a single variable (lexicographic), variations of elimination-by-aspects, equal weighting, hybrids of the preceding, and models exploiting dominance. We use twenty simulated and four empirical datasets for illustration. We further provide an overview by regressing heuristic performance on factors characterizing environments. Overall, sensible heuristics generally yield similar choices in many environments. However, selection of the appropriate heuristic can be important in some regions (e.g., if there is low inter-correlation among attributes/cues). Since our work assumes a hit or miss decision criterion, we conclude by outlining extensions for exploring the effects of different loss functions.

An approach for linking score and audio recordings in Makam music of Turkey

The main information sources to study a particular piece of music are symbolic scores and audio recordings. These are complementary representations of the piece and it isvery useful to have a proper linking between the two of the musically meaningful events. For the case of makam music of Turkey, linking the available scores with the correspondingaudio recordings requires taking the specificities of this music into account, such as the particular tunings, the extensive usage of non-notated expressive elements, and the way in which the performer repeats fragmentsof the score. Moreover, for most of the pieces of the classical repertoire, there is no score written by the original composer. In this paper, we propose a methodology to pair sections of a score to the corresponding fragments of audio recording performances. The pitch information obtained from both sources is used as the common representationto be paired. From an audio recording, fundamental frequency estimation and tuning analysis is done to compute a pitch contour. From the corresponding score, symbolic note names and durations are converted to a syntheticpitch contour. Then, a linking operation is performed between these pitch contours in order to find the best correspondences.The method is tested on a dataset of 11 compositions spanning 44 audio recordings, which are mostly monophonic. An F3-score of 82% and 89% are obtained with automatic and semi-automatic karar detection respectively,showing that the methodology may give us a needed tool for further computational tasks such as form analysis, audio-score alignment and makam recognition.

Parametrització de contorns oberts

Un dels principals problemes quan es realitza un anàlisi de contorns és la gran quantitat de dades implicades en la descripció de la figura. Per resoldre aquesta problemàtica, s’aplica la parametrització que consisteix en obtenir d’un contorn unes dades representatives amb els mínims coeficients possibles, a partir dels quals es podrà reconstruir de nou sense pèrdues molt evidents d’informació. En figures de contorns tancats, la parametrització més estudiada és l’aplicació de la transformada discreta de Fourier (DFT). Aquesta s’aplica a la seqüència de valors que descriu el comportament de les coordenades x i y al llarg de tots els punts que formen el traç. A diferència, en els contorns oberts no es pot aplicar directament la DFT ja que per fer-ho es necessita que el valor de x i de y siguin iguals tan en el primer punt del contorn com en l’últim. Això és degut al fet que la DFT representa sense error senyals periòdics. Si els senyals no acaben en el mateix punt, representa que hi ha una discontinuïtat i apareixen oscil·lacions a la reconstrucció. L’objectiu d’aquest treball és parametritzar contorns oberts amb la mateixa eficiència que s’obté en la parametrització de contorns tancats. Per dur-ho a terme, s’ha dissenyat un programa que permet aplicar la DFT en contorns oberts mitjançant la modificació de les seqüencies de x i y. A més a més, també utilitzant el programari Matlab s’han desenvolupat altres aplicacions que han permès veure diferents aspectes sobre la parametrització i com es comporten els Descriptors El·líptics de Fourier (EFD). Els resultats obtinguts han demostrat que l’aplicació dissenyada permet la parametrització de contorns oberts amb compressions òptimes, fet que facilitarà l’anàlisi quantitatiu de formes en camps com l’ecologia, medicina, geografia, entre d’altres.

Reconeixement de gestos de la mà amb el sensor Kinect

El reconeixement dels gestos de la mà (HGR, Hand Gesture Recognition) és actualment un camp important de recerca degut a la varietat de situacions en les quals és necessari comunicar-se mitjançant signes, com pot ser la comunicació entre persones que utilitzen la llengua de signes i les que no. En aquest projecte es presenta un mètode de reconeixement de gestos de la mà a temps real utilitzant el sensor Kinect per Microsoft Xbox, implementat en un entorn Linux (Ubuntu) amb llenguatge de programació Python i utilitzant la llibreria de visió artifical OpenCV per a processar les dades sobre un ordinador portàtil convencional. Gràcies a la capacitat del sensor Kinect de capturar dades de profunditat d’una escena es poden determinar les posicions i trajectòries dels objectes en 3 dimensions, el que implica poder realitzar una anàlisi complerta a temps real d’una imatge o d’una seqüencia d’imatges. El procediment de reconeixement que es planteja es basa en la segmentació de la imatge per poder treballar únicament amb la mà, en la detecció dels contorns, per després obtenir l’envolupant convexa i els defectes convexos, que finalment han de servir per determinar el nombre de dits i concloure en la interpretació del gest; el resultat final és la transcripció del seu significat en una finestra que serveix d’interfície amb l’interlocutor. L’aplicació permet reconèixer els números del 0 al 5, ja que s’analitza únicament una mà, alguns gestos populars i algunes de les lletres de l’alfabet dactilològic de la llengua de signes catalana. El projecte és doncs, la porta d’entrada al camp del reconeixement de gestos i la base d’un futur sistema de reconeixement de la llengua de signes capaç de transcriure tant els signes dinàmics com l’alfabet dactilològic.

Radio detections towards unidentified variable EGRET sources

A considerable fraction of the -ray sources discovered with the Energetic Gamma-Ray Experiment Telescope (EGRET) remain unidentified. The EGRET sources that have been properly identified are either pulsars or variable sources at both radio and gamma-ray wavelengths. Most of the variable sources are strong radio blazars. However, some low galactic-latitude EGRET sources, with highly variable -ray emission, lack any evident counterpart according to the radio data available until now. Aims. The primary goal of this paper is to identify and characterise the potential radio counterparts of four highly variable -ray sources in the galactic plane through mapping the radio surroundings of the EGRET confidence contours and determining the variable radio sources in the field whenever possible. Methods. We have carried out a radio exploration of the fields of the selected EGRET sources using the Giant Metrewave Radio Telescope (GMRT) interferometer at 21 cm wavelength, with pointings being separated by months. Results. We detected a total of 151 radio sources. Among them, we identified a few radio sources whose flux density has apparently changed on timescales of months. Despite the limitations of our search, their possible variability makes these objects a top-priority target for multiwavelength studies of the potential counterparts of highly variable, unidentified gamma-ray sources.

Statistical modeling of bowing control applied to violin sound synthesis

Excitation-continuous music instrument control patterns are often not explicitly represented in current sound synthesis techniques when applied to automatic performance. Both physical model-based and sample-based synthesis paradigmswould benefit from a flexible and accurate instrument control model, enabling the improvement of naturalness and realism. Wepresent a framework for modeling bowing control parameters inviolin performance. Nearly non-intrusive sensing techniques allow for accurate acquisition of relevant timbre-related bowing control parameter signals.We model the temporal contour of bow velocity, bow pressing force, and bow-bridge distance as sequences of short Bézier cubic curve segments. Considering different articulations, dynamics, and performance contexts, a number of note classes are defined. Contours of bowing parameters in a performance database are analyzed at note-level by following a predefined grammar that dictates characteristics of curve segment sequences for each of the classes in consideration. As a result, contour analysis of bowing parameters of each note yields an optimal representation vector that is sufficient for reconstructing original contours with significant fidelity. From the resulting representation vectors, we construct a statistical model based on Gaussian mixtures suitable for both the analysis and synthesis of bowing parameter contours. By using the estimated models, synthetic contours can be generated through a bow planning algorithm able to reproduce possible constraints caused by the finite length of the bow. Rendered contours are successfully used in two preliminary synthesis frameworks: digital waveguide-based bowed stringphysical modeling and sample-based spectral-domain synthesis.

Parameterization of written signatures based on EFD

In this work we propose a method to quantify written signatures from digitalized images based on the use of Elliptical Fourier Descriptors (EFD). As usually signatures are not represented as a closed contour, and being that a necessary condition in order to apply EFD, we have developed a method that represents the signatures by means of a set of closed contours. One of the advantages of this method is that it can reconstruct the original shape from all the coefficients, or an approximated shape from a reduced set of them finding the appropriate number of EFD coefficients required for preserving the important information in each application. EFD provides accurate frequency information, thus the use of EFD opens many possibilities. The method can be extended to represent other kind of shapes.