Search

Your search keyword '"Vera Candeas, Pedro"' showing total 41 results
Start Over Author "Vera Candeas, Pedro"
41 results on '"Vera Candeas, Pedro"'

1. SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation

Author

Garcia-Martinez, Jaime, Diaz-Guerra, David, Politis, Archontis, Virtanen, Tuomas, Carabias-Orti, Julio J., and Vera-Candeas, Pedro

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound
Abstract

Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources from orchestra recordings has not been extensively explored, largely due to a scarcity of comprehensive and clean (i.e bleed-free) multitrack datasets. In this paper, we introduce a novel multitrack dataset called SynthSOD, developed using a set of simulation techniques to create a realistic (i.e. using high-quality soundfonts), musically motivated, and heterogeneous training set comprising different dynamics, natural tempo changes, styles, and conditions. Moreover, we demonstrate the application of a widely used baseline music separation model trained on our synthesized dataset w.r.t to the well-known EnsembleSet, and evaluate its performance under both synthetic and real-world conditions., Comment: Submitted to the OJSP - ICASSP 2025

Published
2024

2. Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation

Author

Cabanas-Molero, Pablo, Munoz-Montoro, Antonio J., Carabias-Orti, Julio, and Vera-Candeas, Pedro

Subjects
Computer Science - Sound, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

This paper presents a novel approach to sound source separation that leverages spatial information obtained during the recording setup. Our method trains a spatial mixing filter using solo passages to capture information about the room impulse response and transducer response at each sensor location. This pre-trained filter is then integrated into a multichannel non-negative matrix factorization (MNMF) scheme to better capture the variances of different sound sources. The recording setup used in our experiments is the typical setup for orchestra recordings, with a main microphone and a close "cardioid" or "supercardioid" microphone for each section of the orchestra. This makes the proposed method applicable to many existing recordings. Experiments on polyphonic ensembles demonstrate the effectiveness of the proposed framework in separating individual sound sources, improving performance compared to conventional MNMF methods., Comment: Accepted for publication at Forum Acusticum 2023

Published
2023

9. Multiple Instrument Mixtures Source Separation Evaluation Using Instrument-Dependent NMF Models

Author

Rodriguez-Serrano, Francisco J., Carabias-Orti, Julio J., Vera-Candeas, Pedro, Virtanen, Tuomas, Ruiz-Reyes, Nicolas, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Theis, Fabian, editor, Cichocki, Andrzej, editor, Yeredor, Arie, editor, and Zibulevsky, Michael, editor

Published
2012
Full Text
View/download PDF

11. Adaptive Signal Models for Wide-Band Speech and Audio Compression

Author

Vera-Candeas, Pedro, Ruiz-Reyes, Nicolás, Rosa-Zurera, Manuel, Cuevas-Martinez, Juan C., López-Ferreras, Francisco, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Marques, Jorge S., editor, Pérez de la Blanca, Nicolás, editor, and Pina, Pedro, editor

Published
2005
Full Text
View/download PDF

18. Discrimination between transient voltage stability and voltage sag using damped sinusoids-based transient modeling

Author

Ruiz-Reyes, Nicolas, Vera-Candeas, Pedro, and Jurado, Francisco

Subjects
Induction electric motors -- Research, Voltage -- Research, Business, Computers, Electronics, Electronics and electrical industries
Abstract

This paper presents a technique for accurate discrimination between transient voltage stability and voltage sag by combining damped sinusoids-based transient modeling with neural networks. Transient modeling is accomplished by energy adapted matching pursuits with an over-complete dictionary of damped sinusoids. In our approach, the information provided by the damped sinusoids-based transient modeling stage is applied to a Neural Network, which determine in a fast and accurate fashion the class to which the waveform belongs. The simulated results clearly show that the proposed technique can accurately discriminate between transient voltage stability and voltage sag in power system protection. Index Terms--Damped sinusoids, induction motor drives, load modeling, matching pursuit, signal modeling.

Published
2005

23. Source Localization using a Spatial Kernel based Covariance Model and Supervised Complex Nonnegative Matrix Factorization

Author

Montoro, Antonio Jesús Muñoz, Montiel-Zafra, Violeta, Carabias-Orti, Julio José, Torre-Cruz, Juan, Canadas-Quesada, Francisco Jesús, and Vera-Candeas, Pedro

Abstract

Proceedings of the ICA 2019 and EAA Euroregio : 23rd International Congress on Acoustics, integrating 4th EAA Euroregio 2019 : 9-13 September 2019, Aachen, Germany / proceedings editor: Martin Ochmann, Michael Vorländer, Janina Fels 23rd International Congress on Acoustics, integrating 4th EAA Euroregio 2019, ICA 2019, Aachen, Germany, 9 Sep 2019 - 13 Sep 2019; Aachen (2019)., Published by Aachen

Published
2019
Full Text
View/download PDF

31. Desarrollo de técnicas de codificación de audio basadas en modelos de señal paramétricos

Author

Vera Candeas, Pedro, Ruiz Reyes, Nicolás, Rosa Zurera, Manuel, and Universidad de Alcalá. Departamento de Teoría de la Señal y Comunicaciones

Subjects
Telecomunicaciones, Telecommunication, CIENCIAS TECNOLÓGICAS, Ciencias tecnológicas, Señales, Procesado de-Modelos matemáticos, Señales, Teoría de (Telecomunicación), Sonido-Grabación y reproducción digita
Published
2006

38. Adaptive Signal Models for Wide-Band Speech and Audio Compression.

Author

Marques, Jorge S., Pérez de la Blanca, Nicolás, Pina, Pedro, Vera-Candeas, Pedro, Ruiz-Reyes, Nicolás, Rosa-Zurera, Manuel, Cuevas-Martinez, Juan C., and López-Ferreras, Francisco

Abstract

This paper deals with the application of adaptive signal models for parametric speech and audio compression. The matching pursuit algorithm is used for extracting sinusoidal components and transients in audio signals. The resulting residue is perceptually modelled as a noise like signal. When a transient is detected, psychoacoustic-adapted matching pursuits are accomplished using a wavelet-based dictionary followed of an harmonic one. Otherwise, matching pursuit is applied only to the harmonic dictionary. This multi-part model (Sines + Transients + Noise) is successfully applied for speech and audio coding purposes, assuring high perceptual quality at low bit rates (close to 16 kbps for most of the signals considered for testing). [ABSTRACT FROM AUTHOR]

Published
2005
Full Text
View/download PDF

39. Tempo Driven Audio-to-Score Alignment Using Spectral Decomposition and Online Dynamic Time Warping

Author

Rodriguez-Serrano, Francisco Jose, Carabias-Orti, Julio Jose, Vera-Candeas, Pedro, and Martinez-Munoz, Damian

Abstract

In this article, we present an online score following framework designed to deal with automatic accompaniment. The proposed framework is based on spectral factorization and online Dynamic Time Warping (DTW) and has two separated stages: preprocessing and alignment. In the first one, we convert the score into a reference audio signal using a MIDI synthesizer software and we analyze the provided information in order to obtain the spectral patterns (i.e., basis functions) associated to each score unit. In this work, a score unit represents the occurrence of concurrent or isolated notes in the score. These spectral patterns are learned from the synthetic MIDI signal using a method based on Non-negative Matrix Factorization (NMF) with Beta-divergence, where the gains are initialized as the ground-truth transcription inferred from the MIDI. On the second stage, a non-iterative signal decomposition method with fixed spectral patterns per score unit is used over the magnitude spectrogram of the input signal resulting in a distortion matrix that can be interpreted as the cost of the matching for each score unit at each frame. Finally, the relation between the performance and the musical score times is obtained using a strategy based on online DTW, where the optimal path is biased by the speed of interpretation. Our system has been evaluated and compared to other systems, yielding reliable results and performance.

Published
2017
Full Text
View/download PDF

40. Algoritmos de procesado de señal basados en Non-negative Matrix Factorization aplicados a la separación, detección y clasificación de sibilancias en señales de audio respiratorias monocanal

Author

DE LA TORRE CRUZ, JUAN, VERA CANDEAS, PEDRO, CAÑADAS QUESADA, FRANCISCO JESÚS, and Universidad de Jaén. Departamento de INGENIERÍA DE TELECOMUNICACIÓN

Subjects
Sonidos respiratorios normales, Procesado de señal biomédica, Sibilancias, Auscultación
Abstract

La auscultación es el primer examen clínico que un médico lleva a cabo para evaluar el estado del sistema respiratorio, debido a que es un método no invasivo, de bajo coste, fácil de realizar y seguro para el paciente. Sin embargo, el diagnóstico que se deriva de la auscultación sigue siendo un diagnóstico subjetivo que se encuentra condicionado a la habilidad, experiencia y entrenamiento de cada médico en la escucha e interpretación de las señales de audio respiratorias. En consecuencia, se producen un alto porcentaje de diagnósticos erróneos que ponen en riesgo la salud de los pacientes e incrementan el coste asociado a los centros de salud. Esta Tesis propone nuevos métodos basados en Non-negative Matrix Factorization aplicados a la separación, detección y clasificación de sonidos sibilantes para proporcionar una vía de información complementaria al médico que ayude a mejorar la fiabilidad del diagnóstico emitido por el especialista. Auscultation is the first clinical examination that a physician performs to evaluate the condition of the respiratory system, because it is a non-invasive, low-cost, easy-to-perform and safe method for the patient. However, the diagnosis derived from auscultation remains a subjective diagnosis that is conditioned by the ability, experience and training of each physician in the listening and interpretation of respiratory audio signals. As a result, a high percentage of misdiagnoses are produced that endanger the health of patients and increase the cost associated with health centres. This Thesis proposes new methods based on Non-negative Matrix Factorization applied to separation, detection and classification of wheezing sounds in order to provide a complementary information pathway to the physician that helps to improve the reliability of the diagnosis made by the doctor. Tesis Univ. Jaén. Departamento INGENIERÍA DE TELECOMUNICACIÓN

Published
2021

41. Classification and Separation Techniques based on Fundamental Frequency for Speech Enhancement

Author

Cabañas-Molero, Pablo-Antonio, Vera-Candeas, Pedro, Ruiz-Reyes, Nicolás, and Universidad de Jaén. Departamento de Ingeniería de Telecomunicación

Subjects
Hearing aids, 3325.99, Mejora de voz, Speech enhancement, Audífonos digitales, Speech classification, Clasificación de voz, Fundamental frequency, Frecuencia fundamental, Factorización de matrices no negativas, Nonnegative matrix factorization (NMF)
Abstract

[ES] En esta tesis se desarrollan nuevos algoritmos de clasificación y mejora de voz basados en las propiedades de la frecuencia fundamental (F0) de la señal vocal. Estas propiedades permiten su discriminación respecto al resto de señales de la escena acústica, ya sea mediante la definición de características (para clasificación) o la definición de modelos de señal (para separación). Tres contribuciones se aportan en esta tesis: 1) un algoritmo de clasificación de entorno acústico basado en F0 para audífonos digitales, capaz de clasificar la señal en las clases voz y no-voz; 2) un algoritmo de detección de voz sonora basado en la aperiodicidad, capaz de funcionar en ruido no estacionario y con aplicación a mejora de voz; 3) un algoritmo de separación de voz y ruido basado en descomposición NMF, donde el ruido se modela de una forma genérica mediante restricciones matemáticas. [EN]This thesis is focused on the development of new classification and speech enhancement algorithms based, explicitly or implicitly, on the fundamental frequency (F0). The F0 of speech has a number of properties that enable speech discrimination from the remaining signals in the acoustic scene, either by defining F0-based signal features (for classification) or F0-based signal models (for separation). Three main contributions are included in this work: 1) an acoustic environment classification algorithm for hearing aids based on F0 to classify the input signal into speech and nonspeech classes; 2) a frame-by-frame basis voiced speech detection algorithm based on the aperiodicity measure, able to work under non-stationary noise and applicable to speech enhancement; 3) a speech denoising algorithm based on a regularized NMF decomposition, in which the background noise is described in a generic way with mathematical constraints. Tesis Univ. Jaén. Departamento de Ingeniería de Telecomunición. Leída el 11 de enero de 2016

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results