Real-time image processing for crop/weed discrimination in maize fields

This paper presents a computer vision system that successfully discriminates between weed patches and crop rows under uncontrolled lighting in real-time. The system consists of two independent subsystems, a fast image processing delivering results in real-time (Fast Image Processing, FIP), and a slower and more accurate processing (Robust Crop Row Detection, RCRD) that is used to correct the first subsystem's mistakes. This combination produces a system that achieves very good results under a wide variety of conditions. Tested on several maize videos taken of different fields and during different years, the system successfully detects an average of 95% of weeds and 80% of crops under different illumination, soil humidity and weed/crop growth conditions. Moreover, the system has been shown to produce acceptable results even under very difficult conditions, such as in the presence of dramatic sowing errors or abrupt camera movements. The computer vision system has been developed for integration into a treatment system because the ideal setup for any weed sprayer system would include a tool that could provide information on the weeds and crops present at each point in real-time, while the tractor mounting the spraying bar is moving

The ciao modular, standalone compiler and its generic program processing library

Ciao Prolog incorporates a module system which allows sepárate compilation and sensible creation of standalone executables. We describe some of the main aspects of the Ciao modular compiler, ciaoc, which takes advantage of the characteristics of the Ciao Prolog module system to automatically perform sepárate and incremental compilation and efficiently build small, standalone executables with competitive run-time performance, ciaoc can also detect statically a larger number of programming errors. We also present a generic code processing library for handling modular programs, which provides an important part of the functionality of ciaoc. This library allows the development of program analysis and transformation tools in a way that is to some extent orthogonal to the details of module system design, and has been used in the implementation of ciaoc and other Ciao system tools. We also describe the different types of executables which can be generated by the Ciao compiler, which offer different tradeoffs between executable size, startup time, and portability, depending, among other factors, on the linking regime used (static, dynamic, lazy, etc.). Finally, we provide experimental data which illustrate these tradeoffs.

An abstract machine based execution model for computer architecture design and efficient implementation of logic programs in parallel.

The term "Logic Programming" refers to a variety of computer languages and execution models which are based on the traditional concept of Symbolic Logic. The expressive power of these languages offers promise to be of great assistance in facing the programming challenges of present and future symbolic processing applications in Artificial Intelligence, Knowledge-based systems, and many other areas of computing. The sequential execution speed of logic programs has been greatly improved since the advent of the first interpreters. However, higher inference speeds are still required in order to meet the demands of applications such as those contemplated for next generation computer systems. The execution of logic programs in parallel is currently considered a promising strategy for attaining such inference speeds. Logic Programming in turn appears as a suitable programming paradigm for parallel architectures because of the many opportunities for parallel execution present in the implementation of logic programs. This dissertation presents an efficient parallel execution model for logic programs. The model is described from the source language level down to an "Abstract Machine" level suitable for direct implementation on existing parallel systems or for the design of special purpose parallel architectures. Few assumptions are made at the source language level and therefore the techniques developed and the general Abstract Machine design are applicable to a variety of logic (and also functional) languages. These techniques offer efficient solutions to several areas of parallel Logic Programming implementation previously considered problematic or a source of considerable overhead, such as the detection and handling of variable binding conflicts in AND-Parallelism, the specification of control and management of the execution tree, the treatment of distributed backtracking, and goal scheduling and memory management issues, etc. A parallel Abstract Machine design is offered, specifying data areas, operation, and a suitable instruction set. This design is based on extending to a parallel environment the techniques introduced by the Warren Abstract Machine, which have already made very fast and space efficient sequential systems a reality. Therefore, the model herein presented is capable of retaining sequential execution speed similar to that of high performance sequential systems, while extracting additional gains in speed by efficiently implementing parallel execution. These claims are supported by simulations of the Abstract Machine on sample programs.

Discernment of bee pollen loads using computer vision and one-class classification techniques

In this paper, we propose a system for authenticating local bee pollen against fraudulent samples using image processing and classification techniques. Our system is based on the colour properties of bee pollen loads and the use of one-class classifiers to reject unknown pollen samples. The latter classification techniques allow us to tackle the major difficulty of the problem, the existence of many possible fraudulent pollen types. Also presented is a multi-classifier model with an ambiguity discovery process to fuse the output of the one-class classifiers. The method is validated by authenticating Spanish bee pollen types, the overall accuracy of the final system of being 94%. Therefore, the system is able to rapidly reject the non-local pollen samples with inexpensive hardware and without the need to send the product to the laboratory.

TCAD for PV: a fast method for accurately modelling metal impurity evolution during solar cell processing

Coupled device and process silumation tools, collectively known as technology computer-aided design (TCAD), have been used in the integrated circuit industry for over 30 years. These tools allow researchers to quickly converge on optimized devide designs and manufacturing processes with minimal experimental expenditures. The PV industry has been slower to adopt these tools, but is quickly developing competency in using them. This paper introduces a predictive defect engineering paradigm and simulation tool, while demonstrating its effectiveness at increasing the performance and throughput of current industrial processes. the impurity-to-efficiency (I2E) simulator is a coupled process and device simulation tool that links wafer material purity, processing parameters and cell desigh to device performance. The tool has been validated with experimental data and used successfully with partners in industry. The simulator has also been deployed in a free web-accessible applet, which is available for use by the industrial and academic communities.

Sound of lasers (SOL) - An audiovisual approach to semiconductor laser dynamics

We present an educational software addressed to the students of optical communication courses, for a simple visualization of the basic dynamic processes of semiconductor lasers. The graphic interface allows the user to choose the laser and the modulation parameters and it plots the laser power output and instantaneous frequency versus time. Additionally, the optical frequency variations are numerically shifted into the audible frequency range in order to produce a sound wave from the computer loudspeakers. Using the proposed software, the student can simultaneously see and hear how the laser intensity and frequency change, depending on the modulation and device parameters.

Sintetizador analógico en Arduino

Este proyecto consiste en el diseño y construcción de un sintetizador basado en el chip 6581 Sound Interface Device (SID). Este chip era el encargado de la generación de sonido en el Commodore 64, ordenador personal comercializado en 1982, y fue el primer sintetizador complejo construido para ordenador. El chip en cuestión es un sintetizador de tres voces, cada una de ellas capaz de generar cuatro diferentes formas de onda. Cada voz tiene control independiente de varios parámetros, permitiendo una relativamente amplia variedad de sonidos y efectos, muy útil para su uso en videojuegos. Además está dotado de un filtro programable para conseguir distintos timbres mediante síntesis sustractiva. El sintetizador se ha construido sobre Arduino, una plataforma de electrónica abierta concebida para la creación de prototipos, consistente en una placa de circuito impreso con un microcontrolador, programable desde un PC para que realice múltiples funciones (desde encender LEDs hasta controlar servomecanismos en robótica, procesado y transmisión de datos, etc.). El sintetizador es controlable vía MIDI, por ejemplo, desde un teclado de piano. A través de MIDI recibe información tal como qué notas debe tocar, o los valores de los parámetros del SID que modifican las propiedades del sonido. Además, toda esa información también la puede recibir de un PC mediante una conexión USB. Se han construido dos versiones del sintetizador: una versión “hardware”, que utiliza el SID para la generación de sonido, y otra “software”, que reemplaza el SID por un emulador, es decir, un programa que se comporta (en la medida de lo posible) de la misma manera que el SID. El emulador se ha implementado en un microcontrolador Atmega 168 de Atmel, el mismo que utiliza Arduino. ABSTRACT. This project consists on design and construction of a synthesizer which is based on chip 6581 Sound Interface Device (SID). This chip was used for sound generation on the Commodore 64, a home computer presented in 1982, and it was the first complex synthesizer built for computers. The chip is a three-voice synthesizer, each voice capable of generating four different waveforms. Each voice has independent control of several parameters, allowing a relatively wide variety of sounds and effects, very useful for its use on videogames. It also includes a programmable filter, allowing more timbre control via subtractive synthesis. The synthesizer has been built on Arduino, an open-source electronics prototyping platform that consists on a printed circuit board with a microcontroller, which is programmable with a computer to do several functions (lighting LEDs, controlling servomechanisms on robotics, data processing or transmission, etc.). The synthesizer is controlled via MIDI, in example, from a piano-type keyboard. It receives from MIDI information such as the notes that should be played or SID’s parameter values that modify the sound. It also can receive that information from a PC via USB connection. Two versions of the synthesizer have been built: a hardware one that uses the SID chip for sound generation, and a software one that replaces SID by an emulator, it is, a program that behaves (as far as possible) in the same way the SID would. The emulator is implemented on an Atmel’s Atmega 168 microcontroller, the same one that is used on Arduino.

Transductor óptico-sonoro basado en procesado de imagen

En este proyecto se aborda la transducción óptico-sonora utilizando métodos de tratamiento digital de imagen. Para llevar a cabo el proyecto se consideran únicamente métodos de bajo presupuesto, por lo que para realizar todo el proceso de conversión óptico-sonora se utilizan un ordenador y un escáner doméstico. Como el principal objetivo del proyecto es comprobar si es viable utilizar el tratamiento digital de imagen como conversor no se ha contemplado la utilización de equipamiento profesional. La utilidad de este proyecto está en la restauración del sonido de material fílmico con importantes degradaciones, tales que no sea posible su reproducción en un proyector. Con el prototipo que se propone, realizado con el software de programación Matlab, se consigue digitalizar el audio analógico de las películas en malas condiciones ya que la captura de audio se efectúa de manera óptica sobre las bandas sonoras. Lo conseguido en este proyecto cobra especial importancia si se tiene en cuenta la cantidad de material cinematográfico que hay en películas de celulosa. La conservación de dicho material requiere unas condiciones de almacenamiento muy específicas para que el soporte no se vea afectado, pero con el paso del tiempo es habitual que las bobinas de película presenten deformaciones o incluso ruptura. Aplicando métodos de tratamiento digital de imagen es posible restaurar el audio de fragmentos de película que no puedan ser expuestos a la tensión producida por los rodillos de los proyectores, incluso es posible recuperar el audio de fotogramas concretos ya que la digitalización del audio se realiza capturando la imagen de la forma de onda. Por ello, el procedimiento seguido para digitalizar la película debe ser poco intrusivo para garantizar la conservación del soporte fílmico. Cabe destacar que en este proyecto se ha realizado la conversión óptico-sonora sobre las bandas de sonido analógicas de área variable presentes en la película, pero el procedimiento es aplicable también a las bandas de área variable realizando modificaciones en el prototipo. Esto último queda fuera del objetivo de este proyecto, pero puede ser un trabajo futuro. ABSTRACT This project addresses optical to sound conversion using digital image processing methods. To carry out the project are considered only low-budget methods , so for all optical to sound conversion process using a computer and a home scanner . As the main application of this project is to test the feasibility of using the digital image processing as a converter does not contemplate the use of professional equipment. The main objective of this project is the restoration of sound film material with significant impairments , such is not possible playback on a projector. With the proposed prototype , made with Matlab programming software , you get digitize analog audio bad movies because the audio capture is performed optically on the soundtracks. The achievements in this project is especially important if you consider the amount of film material is in cellulose films . The preservation of such material requires a very specific storage conditions to which the support is not affected , but over time it is common for film reels presenting deformations or even rupture. Applying methods of digital image processing is possible to restore the audio from movie clips that can not be exposed to the tension produced by the rollers of the projectors , it is even possible to retrieve specific frames audio and audio that digitization is done by capturing the image of the waveform. Therefore, the procedure used to digitize the film should be bit intrusive to ensure the conservation of the film medium. Note that in this project was carried out optical to sound conversion on analog variable area soundtracks present in the film, but the procedure is applicable to variable-area bands making changes to the prototype. The latter is beyond the scope of this project, but can be a future work.

Evaluation of angle-dependent absorption: Computer simulation and listening test for an objective and subjective evaluation

The aim of this thesis is the subjective and objective evaluation of angledependent absorption coefficients. As the assumption of a constant absorption coefficient over the angle of incidence is not always held, a new model acknowledging an angle-dependent reflection must be considered, to get a more accurate prediction in the sound field. The study provides information about the behavior of different materials in several rooms, depending on the reflection modeling of incident sound waves. An objective evaluation was run for an implementation of angle-dependent reflection factors in the image source and ray tracing simulation models. Results obtained were analysed after comparison to diffuse-field averaged data. However, changes in acoustic characteristics of a room do not always mean a variation in the listener’s perception. Thus, additional subjective evaluation allowed a comparison between the different results obtained with the computer simulation and the response from the individuals who participated in the listening test. The listening test was designed following a three-alternative forced-choice (3AFC) paradigm. In each interaction asked to the subjects a sequence of either three pink noise bursts or three natural signals was alternated. These results were supposed to show the influence and perception of the two different ways to implement surface reflection –either with diffuse or angle-dependent absorption properties. Results show slightly audible effects when material properties were exaggerated. El objetivo de este trabajo es la evaluación objetiva y subjetiva del coeficiente de absorción en función del ángulo de incidencia de la onda de sonido. La suposición de un coeficiente de absorción constante con respecto al ángulo de incidencia no siempre se sostiene. Por ello, un nuevo modelo considerando la reflexión dependiente del ángulo se debe tener en cuenta para obtener predicciones más certeras en el campo del sonido. El estudio proporciona información sobre el comportamiento de diferentes materiales en distintos recintos, dependientes del modelo de reflexión de las ondas de sonido incidentes. Debido a las dificultades a la hora de realizar las medidas y, por lo tanto, a la falta de datos, los coeficientes de absorción dependientes del ángulo a menudo no se tienen en cuenta a la hora de realizar las simulaciones. Hoy en día, aún no hay una tendencia de aplicar el coeficiente de absorción dependiente del ángulo para mejorar los modelos de reflexión. Por otra parte, para una medición satisfactoria de la absorción dependiente del ángulo, sólo hay unos pocos métodos. Las técnicas de medición actuales llevan mucho tiempo y hay algunos materiales, condiciones y ángulos que no pueden ser reproducidos y, por lo tanto, no es posible su medición. Sin embargo, en el presente estudio, los ángulos de incidencia de las ondas de sonido son conocidos y almacenados en una de base de datos para cada uno de los materiales, de modo que los coeficientes de absorción para el ángulo dado pueden ser devueltos siempre que sean requeridos por el usuario. Para realizar el estudio se llevó a cabo una evaluación objetiva, por medio de la implementación del factor de reflexión dependiente del ángulo en los modelos de fuentes imagen y trazado de rayos. Los resultados fueron analizados después de ser comparados con el promedio de los datos obtenidos en medidas en el campo difuso. La simulación se hizo una vez se configuraron un número de materiales creados por el autor, a partir de los datos existentes en la literatura y los catálogos de fabricantes. Los modelos de Komatsu y Mechel sirvieron como referencia para los materiales porosos, configurando la resistividad al aire o el grosor, y para los paneles perforados, introduciendo el radio de los orificios y la distancia entre centros, respectivamente. Estos materiales se situaban en la pared opuesta a la que se consideraba que debía alojar a la fuente sonora. El resto de superficies se modelaban con el mismo material, variando su coeficiente de absorción y/o de dispersión. Al mismo tiempo, una serie de recintos fueron modelados para poder reproducir distintos escenarios de los que obtener los resultados. Sin embargo, los cambios en las características acústicas de un recinto no significan variaciones en la percepción por parte del oyente. Por ello, una evaluación subjetiva adicional permitió una comparación entre los diferentes resultados obtenidos mediante la simulación informática y la respuesta de los individuos que participaron en la prueba de escucha. Ésta fue diseñada bajo las pautas del modelo de test three-alternative forced-choice (3AFC), con treinta y dos preguntas diferentes. En cada iteración los sujetos fueron preguntados por una secuencia alterna entre tres señales, siendo dos de ellas iguales. Éstas podían ser tanto ráfagas de ruido rosa como señales naturales, en este test se utilizó un fragmento de una obra clásica interpretada por un piano. Antes de contestar al cuestionario, los bloques de preguntas eran ordenados al azar. Para cada ensayo, la mezcla era diferente, así los sujetos no repetían la misma prueba, evitando un sesgo por efectos de aprendizaje. Los bloques se barajaban recordando siempre el orden inicial, para después almacenar los resultados reordenados. La prueba de escucha fue realizada por veintitrés personas, toda ellas con conocimientos dentro del campo de la acústica. Antes de llevar a cabo la prueba de escucha en un entorno adecuado, una hoja con las instrucciones fue facilitada a cada persona. Los resultados muestran la influencia y percepción de las dos maneras distintas de implementar las reflexiones de una superficie –ya sea con respecto a la propiedad de difusión o de absorción dependiente del ángulo de los materiales. Los resultados objetivos, después de ejecutar las simulaciones, muestran los datos medios obtenidos para comprender el comportamiento de distintos materiales de acuerdo con el modelo de reflexión utilizado en el caso de estudio. En las tablas proporcionadas en la memoria se muestran los valores del tiempo de reverberación, la claridad y el tiempo de caída temprana. Los datos de las características del recinto obtenidos en este análisis tienen una fuerte dependencia respecto al coeficiente de absorción de los diferentes materiales que recubren las superficies del cuarto. En los resultados subjetivos, la media de percepción, a la hora de distinguir las distintas señales, por parte de los sujetos, se situó significativamente por debajo del umbral marcado por el punto de inflexión de la función psicométrica. Sin embargo, es posible concluir que la mayoría de los individuos tienden a ser capaces de detectar alguna diferencia entre los estímulos presentados en el 3AFC test. En conclusión, la hipótesis de que los valores del coeficiente de absorción dependiente del ángulo difieren es contrastada. Pero la respuesta subjetiva de los individuos muestra que únicamente hay ligeras variaciones en la percepción si el coeficiente varía en intervalos pequeños entre los valores manejados en la simulación. Además, si los parámetros de los materiales acústicos no son exagerados, los sujetos no perciben ninguna variación. Los primeros resultados obtenidos, proporcionando información respecto a la dependencia del ángulo, llevan a una nueva consideración en el campo de la acústica, y en la realización de nuevos proyectos en el futuro. Para futuras líneas de investigación, las simulaciones se deberían realizar con distintos tipos de recintos, buscando escenarios con geometrías irregulares. También, la implementación de distintos materiales para obtener resultados más certeros. Otra de las fases de los futuros proyectos puede realizarse teniendo en cuenta el coeficiente de dispersión dependiente del ángulo de incidencia de la onda de sonido. En la parte de la evaluación subjetiva, realizar una serie de pruebas de escucha con distintos individuos, incluyendo personas sin una formación relacionada con la ingeniería acústica.

Procedure for verification of sound source coverage over façades according to the International Standard ISO 140-5

This paper presents a new verification procedure for sound source coverage according to ISO 140?5 requirements. The ISO 140?5 standard applies to the measurement of façade insulation and requires a sound source able to achieve a sufficiently uniform sound field in free field conditions on the façade under study. The proposed method involves the electroacoustic characterisation of the sound source in laboratory free field conditions (anechoic room) and the subsequent prediction by computer simulation of the sound free field radiated on a rectangular surface equal in size to the façade being measured. The loudspeaker is characterised in an anechoic room under laboratory controlled conditions, carefully measuring directivity, and then a computer model is designed to calculate the acoustic free field coverage for different loudspeaker positions and façade sizes. For each sound source position, the method provides the maximum direct acoustic level differences on a façade specimen and therefore determines whether the loudspeaker verifies the maximum allowed level difference of 5 dB (or 10 dB for façade dimensions greater than 5 m) required by the ISO standard. Additionally, the maximum horizontal dimension of the façade meeting the standard is calculated and provided for each sound source position, both with the 5 dB and 10 dB criteria. In the last section of the paper, the proposed procedure is compared with another method used by the authors in the past to achieve the same purpose: in situ outdoor measurements attempting to recreate free field conditions. From this comparison, it is concluded that the proposed method is able to reproduce the actual measurements with high accuracy, for example, the ground reflection effect, at least at low frequencies, which is difficult to avoid in the outdoor measurement method, and it is fully eliminated with the proposed method to achieve the free field requisite.

Web based interactive educational software introducing semiconductor laser dynamics: Sound Of Lasers (SOL)

In this work, educational software for intuitive understanding of the basic dynamic processes of semiconductor lasers is presented. The proposed tool is addressed to the students of optical communication courses, encouraging self consolidation of the subjects learned in lectures. The semiconductor laser model is based on the well known rate equations for the carrier density, photon density and optical phase. The direct modulation of the laser is considered with input parameters which can be selected by the user. Different options for the waveform, amplitude and frequency of thpoint. Simulation results are plotted for carrier density and output power versus time. Instantaneous frequency variations of the laser output are numerically shifted to the audible frequency range and sent to the computer loudspeakers. This results in an intuitive description of the “chirp” phenomenon due to amplitude-phase coupling, typical of directly modulated semiconductor lasers. In this way, the student can actually listen to the time resolved spectral content of the laser output. By changing the laser parameters and/or the modulation parameters,consequent variation of the laser output can be appreciated in intuitive manner. The proposed educational tool has been previously implemented by the same authors with locally executable software. In the present manuscript, we extend our previous work to a web based platform, offering improved distribution and allowing its use to the wide audience of the web.

KATS: A Knowledge Acquisition Tool Based on Electronic Document Processing

This paper describes a particular knowledge acquisition tool for the construction and maintenance of the knowledge model of an intelligent system for emergency management in the field of hydrology. This tool has been developed following an innovative approach directed to end-users non familiarized in computer oriented terminology. According to this approach, the tool is conceived as a document processor specialized in a particular domain (hydrology) in such a way that the whole knowledge model is viewed by the user as an electronic document. The paper first describes the characteristics of the knowledge model of the intelligent system and summarizes the problems that we found during the development and maintenance of such type of model. Then, the paper describes the KATS tool, a software application that we have designed to help in this task to be used by users who are not experts in computer programming. Finally, the paper shows a comparison between KATS and other approaches for knowledge acquisition.

AquaData and AquaGIS: Two computer utilities for temporal and spatial simulations of water-limited yield with AquaCrop.

The crop simulation model AquaCrop, recently developed by FAO can be used for a wide range of purposes. However, in its present form, its use over large areas or for applications that require a large number of simulations runs (e.g., long-term analysis), is not practical without developing software to facilitate such applications. Two tools for managing the inputs and outputs of AquaCrop, named AquaData and AquaGIS, have been developed for this purpose and are presented here. Both software utilities have been programmed in Delphi v. 5 and in addition, AquaGIS requires the Geographic Information System (GIS) programming tool MapObjects. These utilities allow the efficient management of input and output files, along with a GIS module to develop spatial analysis and effect spatial visualization of the results, facilitating knowledge dissemination. A sample of application of the utilities is given here, as an AquaCrop simulation analysis of impact of climate change on wheat yield in Southern Spain, which requires extensive input data preparation and output processing. The use of AquaCrop without the two utilities would have required approximately 1000 h of work, while the utilization of AquaData and AquaGIS reduced that time by more than 99%. Furthermore, the use of GIS, made it possible to perform a spatial analysis of the results, thus providing a new option to extend the use of the AquaCrop model to scales requiring spatial and temporal analyses.

Characterization of speech from amyotrophic lateral sclerosis by neuromorphic processing

Amyotrophic Lateral Sclerosis is a severe disease, which dramatically reduces the speech communication skills of patients as disease progresses. The present study is devoted to define accurate and objective estimates to characterize the loss of communication skills, to help clinicians and therapists in monitoring disease progression and in deciding on rehabilitation interventions. The methodology proposed is based on the perceptual (neuromorphic)definition of speech dinamics, concentrated in vowel sound in character and duration. We present the results from a longitudinal study carried out in an ALS patient during one year. Discussion addresses future actions.

Synchronizing sound from different devices over a TCP network

Nowadays, we can send audio on the Internet for multiples uses like telephony, broadcast audio or teleconferencing. The issue comes when you need to synchronize the sound from different sources because the network where we are going to work could lose packets and introduce delay in the delivery. This can also come because the sound cards could be work in different speeds. In this project, we will work with two computers emitting sound (one will simulate the left channel (mono) of a stereo signal, and the other the right channel) and connected with a third computer by a TCP network. The last computer must get the sound from both computers and reproduce it in a speaker properly (without delay). So, basically, the main goal of the project is to synchronize multi-track sound over a network. TCP networks introduce latency into data transfers. Streaming audio suffers from two problems: a delay and an offset between the channels. This project explores the causes of latency, investigates the affect of the inter-channel offset and proposes a solution to synchronize the received channels. In conclusion, a good synchronization of the sound is required in a time when several audio applications are being developed. When two devices are ready to send audio over a network, this multi-track sound will arrive at the third computer with an offset giving a negative effect to the listener. This project has dealt with this offset achieving a good synchronization of the multitrack sound getting a good effect on the listener. This was achieved thanks to the division of the project into several steps having constantly a good vision of the problem, a good scalability and having controlled the latency at all times. As we can see in the chapter 4 of the project, a lack of synchronization over c. 100μs is audible to the listener. RESUMEN. A día de hoy, podemos transmitir audio a través de Internet por varios motivos como pueden ser: una llamada telefónica, una emisión de audio o una teleconferencia. El problema viene cuando necesitas sincronizar ese sonido producido por los diferentes orígenes ya que la red a la que nos vamos a conectar puede perder los paquetes y/o introducir un retardo en las entregas de los mismos. Así mismo, estos retardos también pueden venir producidos por las diferentes velocidades a las que trabajan las tarjetas de sonido de cada dispositivo. En este proyecto, se ha trabajado con dos ordenadores emitiendo sonido de manera intermitente (uno se encargará de simular el canal izquierdo (mono) de la señal estéreo emitida, y el otro del canal derecho), estando conectados a través de una red TCP a un tercer ordenador, el cual debe recibir el sonido y reproducirlo en unos altavoces adecuadamente y sin retardo (deberá juntar los dos canales y reproducirlo como si de estéreo de tratara). Así, el objetivo principal de este proyecto es el de encontrar la manera de sincronizar el sonido producido por los dos ordenadores y escuchar el conjunto en unos altavoces finales. Las redes TCP introducen latencia en la transferencia de datos. El streaming de audio emitido a través de una red de este tipo puede sufrir dos grandes contratiempos: retardo y offset, los dos existentes en las comunicaciones entre ambos canales. Este proyecto se centra en las causas de ese retardo, investiga el efecto que provoca el offset entre ambos canales y propone una solución para sincronizar los canales en el dispositivo receptor. Para terminar, una buena sincronización del sonido es requerida en una época donde las aplicaciones de audio se están desarrollando continuamente. Cuando los dos dispositivos estén preparados para enviar audio a través de la red, la señal de sonido multi-canal llegará al tercer ordenador con un offset añadido, por lo que resultará en una mala experiencia en la escucha final. En este proyecto se ha tenido que lidiar con ese offset mencionado anteriormente y se ha conseguido una buena sincronización del sonido multi-canal obteniendo un buen efecto en la escucha final. Esto ha sido posible gracias a una división del proyecto en diversas etapas que proporcionaban la facilidad de poder solucionar los errores en cada paso dando una importante visión del problema y teniendo controlada la latencia en todo momento. Como se puede ver en el capítulo 4 del proyecto, la falta de sincronización sobre una diferencia de 100μs entre dos canales (offset) empieza a ser audible en la escucha final.