Ingeniería eléctrica
Browse by
Recent Submissions
-
2D SLAM Algorithms Characterization, Calibration, and Comparison Considering Pose Error, Map Accuracy, CPU Usage, and Memory Usage
(2022)The present work proposes a method to characterize, calibrate, and compare, any 2D SLAM algorithm, providing strong statistical evidence, based on descriptive and inferential statistics to bring confidence levels about ... -
Producción artificial de habla: Síntesis de voz
(2015)A finales de la década de los 80, el estadounidense Raymond Kurzweil, inventor del primer sistema comercial que es capaz de tomar texto de un libro y pronunciarlo mediante habla artificial, escribió la obra “La era de las ... -
Ejemplo de generación y clasificación de bases de datos de imágenes simples
(2015)Se documenta la creación de una base de datos para clasificación, que consiste de patrones de imágenes simples. Se presentan resultados de una clasificación de estas imágenes utilizando redes neuronales tipo perceptrón ... -
Minería de Datos: Concepto y Aplicaciones
(2014)Se presenta la minería de datos como un conjunto de técnicas para obtener información útil y no evidente en datos de diversos tipos. Primero se revisa el concepto y su evolución, para repasar varias de las aplicaciones ... -
Inteligencia Artificial en la Creación Musical
(2013)Se presenta el desarrollo de las técnicas de inteligencia artificial en procesos de creación musical, tanto para el apoyo de creación de obras a los compositores, como en proyectos que pretenden automatizar todo el proceso. ... -
HMM-Based Speech Synthesis Enhancement with Hybrid Postfilters
(2018)In this chapter, we introduce hybrid postfilters into speech synthesis, with the objective of enhancing the quality of the synthesized speech. Our approach combines a Wiener filter with deep neural networks. Several ... -
Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement
(2020)Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One ... -
Auto-Associative Initialization of LSTM Neural Networks for Fundamental Frequency Detection in Noisy Speech Signals
(2018)In this paper, we present a new approach for fundamental frequency detection in noisy speech, based on Long Short-term Memory Neural Networks (LSTM). Fundamental frequency is one of the most important parameters of human ... -
Desarrollo de Tecnologías del Habla en Costa Rica
(2020)Las tecnologías del habla son un conjunto de conocimientos, técnicas y recursos empleados para propiciar la interacción de las personas con dispositivos electrónicos, o bien entre personas con mediación de un dispositivo. ... -
Metodología para la construcción de voces artificiales para la educación inclusiva
(2021)La integración de voces artificiales en dispositivos tecnológicos es una opción para favorecer la comunicación en personas con discapacidad, ya que permite mayores herramientas para la inclusión de esta población, haciendo ... -
Speech synthesis based on Hidden Markov Models and deep learning
(2016)Speech synthesis based on Hidden Markov Models (HMM) and other statistical parametric techniques have been a hot topic for some time. Using this techniques, speech synthesizers are able to produce intelligible and ... -
Improving automatic speech recognition containing additive noise using deep denoising autoencoders of lstm networks
(2016)Automatic speech recognition systems (ASR) suffer from performance degradation under noisy conditions. Recent work, using deep neural networks to denoise spectral input features for robust ASR, have proved to be successful. ... -
Hybrid speech enhancement with wiener filters and deep LSTM denoising autoencoders
(2018)Over the past several decades, numerous speech enhancement techniques have been proposed to improve the performance of modern communication devices in noisy environments. Among them, there is a large range of classical ... -
LSTM deep neural networks postfiltering for improving the quality of synthetic voices
(2016)Recent developments in speech synthesis have produced systems capable of providing intelligible speech, and researchers now strive to create models that more accurately mimic human voices. One such development is the ... -
Pre-training Long Short-term Memory neural networks for efficient regression in artificial speech postfiltering
(2018)Several attempts to enhance statistical parametric speech synthesis have contemplated deep-learning-based postfilters, which learn to perform a mapping of the synthetic speech parameters to the natural ones, reducing the ... -
Hidden Markov Models for artificial voice production and accent modification
(2016)In this paper, we consider the problem of accent modification between Castilian Spanish and Mexican Spanish. This is an interesting application area for tasks such as the automatic dubbing of pictures and videos with ... -
LSTM deep neural networks postfiltering for enhancing synthetic voices
(2018)Recent developments in speech synthesis have produced systems capable of producing speech which closely resembles natural speech, and researchers now strive to create models that more accurately mimic human voices. One ... -
Robustness of LSTM neural networks for the enhancement of spectral parameters in noisy speech signals
(2019)In this paper, we carry out a comparative performance analysis of Long Short-term Memory (LSTM) Neural Networks for the task of noise reduction. Recent work in this area has shown the advantages of this kind of network for ... -
Improving post-filtering of artificial speech using pre-trained LSTM neural networks
(2019)Several researchers have contemplated deep learning-based post-filters to increase the quality of statistical parametric speech synthesis, which perform a mapping of the synthetic speech to the natural speech, considering ... -
Tecnologías del habla para la educación inclusiva
(2020-01)Existen condiciones de discapacidad que comprometen la habilidad de las personas para expresarse utilizando su voz. Esto puede constituir una limitante para la comunicación, y una barrera para la inclusión de estudiantes ...