Ara es mostren els items 1-20 de 23

    • A unity based validation model for rendering algorithms of motion tracked binaural recordings 

      Rendé Subias, Clara (Universitat Politècnica de Catalunya, 2017-01)
      Treball Final de Grau
      Accés obert
      Realitzat a/amb:   Technische Universität Berlin
      In 2004, motion-tracked binaural (MTB) sound was introduced as a new method for capturing, recording and reproducing spatial sound. In November 2010, the Technische Universität Berlin (TUB) started to evaluate MTB recordings ...
    • Acoustic event detection and classification 

      Temko, Andriy (Universitat Politècnica de Catalunya, 2007-01-23)
      Tesi
      Accés obert
      L'activitat humana que té lloc en sales de reunions o aules d'ensenyament es veu reflectida en una rica varietat d'events acústics, ja siguin produïts pel cos humà o per objectes que les persones manegen. Per això, la ...
    • Acoustic event detection and localization using distributed microphone arrays 

      Chakraborty, Rupayan (Universitat Politècnica de Catalunya, 2013-12-18)
      Tesi
      Accés obert
      Automatic acoustic scene analysis is a complex task that involves several functionalities: detection (time), localization (space), separation, recognition, etc. This thesis focuses on both acoustic event detection (AED) ...
    • An information-theoretic string matching approach for spoken utterance verification and keyword spotting 

      Quer Romeo, Guillem (Universitat Politècnica de Catalunya, 2016)
      Projecte/Treball Final de Carrera
      Accés restringit per decisió de l'autor
      The goal of this project is to develop an information-theoretic acoustic-phonetic approach to detect the presence of words or phrases in an utterance. Specifically, the project focuses on two types of detection tasks in ...
    • Android Implementation of a Visualisation, Sonification and AI-Assisted Interpretation of Neonatal EEG 

      Salgado Burruezo, Eduard (Universitat Politècnica de Catalunya, 2018-05)
      Treball Final de Grau
      Accés obert
      The aim of this project is the implementation of an Android App to help healthcare professionals to check newborn health status by observing neonatal EEG signals, without having extensive training in EEG interpretation. ...
    • Automatic analysis of the acoustic environment of a preterm infant in a neonatal intensive care unit 

      Raboshchuk, Ganna (Universitat Politècnica de Catalunya, 2016-07-20)
      Tesi
      Accés obert
      Most preterm newborns must be admitted to a Neonatal Intensive Care Unit (NICU) where they receive a specialized medical care, what, in many cases, is crucial for their survival. The acoustic environment of a typical NICU ...
    • Birds Sound Detection Using Convolutional Neural Networks 

      Solé Franquesa, Llorenç (Universitat Politècnica de Catalunya, 2019-05)
      Treball Final de Grau
      Accés obert
      The objective of this thesis is to learn how to train and test a Deep Neural Network (DNN). For that purpose, after reviewing recent works, we have chosen the bird sound detection task of the DCASE Challenge 2018, that ...
    • Channel selection and reverberation-robust automatic speech recognition 

      Wolf, Martin (Universitat Politècnica de Catalunya, 2013-11-11)
      Tesi
      Accés obert
      If speech is acquired by a close-talking microphone in a controlled and noise-free environment, current state-of-the-art recognition systems often show an acceptable error rate. The use of close-talking microphones, however, ...
    • Chord recognition in real time 

      Juvillà García, Marc (Universitat Politècnica de Catalunya, 2014-07-25)
      Treball Final de Grau
      Accés obert
      [ANGLÈS] This project is intended to show the viability of doing automatic chord recognition in real time. Actually, a system which acquires audio information and automatically recognizes the underlying musical chords in ...
    • Design of a web graphic user interface for real-time EGG interpretation 

      Peña Romero, Víctor (Universitat Politècnica de Catalunya, 2020-02)
      Treball Final de Grau
      Accés obert
      This project proposes a method for easier interpretation of Electroencephalogram (EEG) data acquired from newborn babies so that it can be understood by a wider range of medical professionals. The equipment currently used ...
    • Deteccció de sons d'ocells amb aprenentatge profund 

      de Blas Álvarez, Maria (Universitat Politècnica de Catalunya, 2018-10)
      Treball Final de Grau
      Accés obert
      One of the keys to artificial intelligence (AI) is automatic learning, and currently one of the most prominent detection and classification techniques is based on convolutive neural networks (CNNs). This is the case in ...
    • EEG seizure detection in paediatrics using deep convolutional neural networks 

      Bauxell Cornet, Joaquim (Universitat Politècnica de Catalunya, 2022-10-14)
      Projecte Final de Màster Oficial
      Accés restringit per acord de confidencialitat
      Realitzat a/amb:   University College, Cork
      Neonate seizure detection using tools such as machine learning is a well researched topic. However, there is still much to be known about how those detection models perform across different age ranges and if a generalised ...
    • Estudi de detecció de sons en un entorn de dispositiu mòbil 

      Arcas Ruscalleda, Jordi (Universitat Politècnica de Catalunya, 2014-07-23)
      Projecte/Treball Final de Carrera
      Accés obert
      [ANGLÈS] In recent years the use of smartphones has been increasing among the society. Such devices allow the development of different applications which have a direct impact for the end user. Different systems of recognition ...
    • Feature selection for multimodal: acoustic event detection 

      Butko, Taras (Universitat Politècnica de Catalunya, 2011-07-08)
      Tesi
      Accés obert
      The detection of the Acoustic Events (AEs) naturally produced in a meeting room may help to describe the human and social activity. The automatic description of interactions between humans and environment can be useful for ...
    • Portable neonatal EEG monitoring and sonification on an Android Device 

      Poveda Pena, Jonatan (Universitat Politècnica de Catalunya, 2017-05)
      Treball Final de Grau
      Accés obert
      Realitzat a/amb:   University College Cork
      In this work a real-time and portable software to check the brain status of preterm babies is implemented using an EEG sonification algorithm based on a Phase Vocoder, faster, cheaper and easier to use than the current ...
    • Quantitative assessment of IA-assisted sound-based interpretation of neonatal EEG 

      Anglès Cabau, Montserrat (Universitat Politècnica de Catalunya, 2018-10)
      Treball Final de Grau
      Accés obert
      The goal of the project was to study the usability of Neurobell, an Android App designed to help healthcare professionals without EEG interpretation expertise. The application, which is currently being developed, detects ...
    • Reconeixement d'àudio en una sala de reunions mitjançant HMM 

      González Pla, Francisco (Universitat Politècnica de Catalunya, 2011-06-21)
      Projecte/Treball Final de Carrera
      Accés obert
      English: In this Master Thesis, an acoustic event detector is proposed working in real-time in a meeting room environment. Real-time processing is a requirement for many practical signal processing applications. Furthermore, ...
    • Robust solutions for audio fingerprinting 

      Amorós i Cortiella, Macià (Universitat Politècnica de Catalunya, 2023-02-01)
      Projecte Final de Màster Oficial
      Accés obert
      This project is focused on the development of an audio-denoising system to improve the robustness of audio fingerprinting algorithms. The state of the art on deep learning has advanced in the last years, specifically in ...
    • Speech recognition system based on auditory features 

      Martin Latorre, Ignacio (Universitat Politècnica de Catalunya, 2008-10-28)
      Projecte/Treball Final de Carrera
      Accés obert
    • Stock prediction with machine learning 

      Rubio Jornet, Víctor (Universitat Politècnica de Catalunya, 2021-02)
      Treball Final de Grau
      Accés obert
      During the last few months, there has been increased attention in the stock market due to the Covid pandemic. The new-found leisure time has driven many people to buy and sell stocks without any knowledge on the matter at ...