Esta tesis doctoral presenta un nuevo enfoque en el área de la transcripción musical automática (AMT), definiendo la tarea de Audio-to-Score (A2S), que realiza la transcripción musical de extremo a extremo gracias a la capacidad de modelado de problemas que nos ofrecen las redes neuronales profundas. Este enfoque va un paso más allá de los sistemas de transcripción tradicionales, que están basados en predecir notas musicales en el formato de tiempo-frecuencia llamado pianola o piano-roll en inglés. Las principales ventajas del enfoque propuesto frente a los métodos tradicionales son las siguientes: - La salida es una partitura válida de música que puede ser directamente interpretada por músicos o analizada por musicólogos. - La aproximación extremo a extremo evita que los errores de una etapa se propaguen a la siguiente. - No precisa de anotaciones de alineamiento temporal entre el audio de entrada y la partitura de salida, dado que se aprende por el modelo de forma implícita. - Mediante la aproximación extremo a extremo se aprende también un modelo de lenguaje musical que ayuda a reducir los errores de transcripción de manera global.

Background:The background of this research lies in detecting the images from satellites. The recognition of images from satellites has become increasingly importantdue to the vast amount of data that can be obtained from satellites. This thesisaims to develop a method for the recognition of images from satellites using machinelearning techniques. Objective:The main objective of this thesis is a unique approach to recognizingthe data with a CRNN algorithm that involves image recognition in satellite imagesusing machine learning, specifically the CRNN (Convolutional Recurrent Neural Network) architecture. The main task is classifying the images accurately, and this isachieved by utilizing object classification algorithms. The CRNN architecture ischosen because it can effectively extract features from satellite images using Convolutional Blocks and leverage the great memory power of the Long Short-TermMemory (LSTM) networks to connect the extracted features efficiently. The connected features improve the accuracy of our model significantly. Method:The proposed method involves doing a literature review to find currentimage recognition models and then experimentation by training a CRNN, CNN andRNN and then comparing their performance using metrics mentioned in the thesis work. Results:The performance of the proposed method is evaluated using various metrics, including precision, recall, F1 score and inference speed, on a large dataset oflabeled images. The results indicate that high accuracy is achieved in detecting andclassifying objects in satellite images through our approach. The potential utilization of our proposed method can span various applications such as environmentalmonitoring, urban planning, and disaster management. Conclusion:The classification on the satellite images is performed using the 2 datasetsfor ships and cars. The proposed architectures are CRNN, CNN, and RNN. These3 models are compared in order to find the best performing algorithm. The resultsindicate that CRNN has the best accuracy and precision and F1 score and inferencespeed, indicating a strong performance by the CRNN. Keywords: Comparison of CRNN, CNN, and RNN, Image recognition, MachineLearning, Algorithms,You Only Look Once. Version3, Satellite images, Aerial Images, Deep Learning

No description available.