Ara es mostren els items 1-20 de 30

  • Adaptació d'entonació entre locutors per sistemes de síntesi de veu 

    Rosell Angliano, Albert (Universitat Politècnica de Catalunya, 2012-01-12)
    Projecte/Treball Final de Carrera
    Accés obert
    English: Proposal of different adaptation methods for pitch in voice synthesizers. Implementation and evaluation. Some common utilized classic methods will be implemented as well to compare the performance with the proposed ...
  • An evaluation of the impact of body movement data in automatic music generation processes with long short-term memory neural networks 

    Tantinyà Vidal, Àgata (Universitat Politècnica de Catalunya, 2017)
    Treball Final de Grau
    Accés obert
    Realitzat a/amb:  University of Limerick
    El aprendizaje automático está ganando popularidad en el campo artístico y la generación de música. El uso del aprendizaje profundo para crear canciones subjetivamente convincentes ha sido un área activa de investigación ...
  • Automatic Drums Transcription for polyphonic music using Non-Negative Matrix Factor Deconvolution 

    Pons i Puig, Jordi (Universitat Politècnica de Catalunya, 2014-07-22)
    Treball Final de Grau
    Accés restringit per acord de confidencialitat
  • Automatic robust classification of speech using analytical feature techniques 

    Calvo Pérez, Gonçal (Universitat Politècnica de Catalunya, 2009-02-02)
    Projecte/Treball Final de Carrera
    Accés obert
    Aquest document és la memòria de la recerca efectuada dins del domini de la classificació automàtica de la parla durant una estada al laboratori Sony CSL per a la realització del projecte fi de carrera. El treball explora ...
  • Automatic transcription for polyphonic music 

    Martín Valero, Juan (Universitat Politècnica de Catalunya, 2016-05)
    Treball Final de Grau
    Accés obert
    We are living times where technology and music go hand in hand, and everyday more musicians and producers integrate new music software into their workflow. This project is the study and development of a first prototype for ...
  • Corpus lingüístic pel desenvolupament d'una veu sintètica en català per a Festival 

    Gallego Gonzàlez, Silvia (Universitat Politècnica de Catalunya, 2010-06)
    Projecte/Treball Final de Carrera
    Accés obert
  • Deep learning applied to speech synthesis 

    Pascual de la Puente, Santiago (Universitat Politècnica de Catalunya, 2016-06-30)
    Projecte Final de Màster Oficial
    Accés obert
    Deep Learning has been applied successfully to speech processing problems. In this work we explore its capabilities, focusing concretely in recurrent neural architectures to build a state of the art Text-To-Speech system ...
  • Disseny d'interfície de control gràfica per transformació de veu 

    Pascual de La Puente, Santiago (Universitat Politècnica de Catalunya, 2013-07-26)
    Treball Final de Grau
    Accés obert
    [ANGLÈS] In this project we have developed a set of interfaces in Android to control a speech synthesis system in real time. This has involved the design and implementation of all components of the interaction, such as: ...
  • Effects of room acoustics on players' perceptions in audio games 

    Sánchez Cervera, Ariadna (Universitat Politècnica de Catalunya, 2017)
    Treball Final de Grau
    Accés obert
    Realitzat a/amb:  University of Limerick
    En tiempos recientes, la evolución de los videojuegos ha sido posible debido a la mejora de sus contenidos visuales, para así recrear la realidad lo más rigurosamente posible. A pesar de ello, los contenidos de audio no ...
  • Emotion recognition based on the speech, using a Naive Bayes classifier 

    Urbano Romeu, Ángel (Universitat Politècnica de Catalunya, 2016-06-30)
    Treball Final de Grau
    Accés obert
    Realitzat a/amb:  Institut für Computertechnik
    Speech emotion recognition is one of the latest challenges in speech processing. Besides facial expressions or gestures, speech has proven as one of the most promising modalities for the automatic emotion recognition. To ...
  • End-to-End photoplethysmography-based biometric authentication system by using deep neural networks 

    Cortès Sebastià, Guillem (Universitat Politècnica de Catalunya, 2018-06)
    Treball Final de Grau
    Accés obert
    Realitzat a/amb:  Telefónica I+D
    Whilst research efforts have traditionally focused on Electrocardiographic (ECG) signals and handcrafted features as potential biometric traits, few works have explored systems based on the raw photoplethysmogram (PPG) ...
  • Expressive speech synthesis from Broadcast News 

    Luzón Tuells, Joaquín (Universitat Politècnica de Catalunya, 2016-09-28)
    Treball Final de Grau
    Accés obert
    Speech Synthesis is the computer process of converting text to voice. This project consists in the synthesis of voices that can tell news with an appropriate expression, since it is important to achieve expressiveness on ...
  • Grapheme-to-phoneme conversion in the era of globalization 

    Polyàkova, Tatyana V. (Universitat Politècnica de Catalunya, 2015-03-13)
    Tesi
    Accés obert
    This thesis focuses on the phonetic transcription in the framework of text-to-speech conversion, especially on improving adaptability, reliability and multilingual support in the phonetic module. The language is constantly ...
  • Measuring the evolution of timbre in Billboard Hot 100 

    Pons Albà, Aleu (Universitat Politècnica de Catalunya, 2017-06-26)
    Treball Final de Grau
    Accés obert
    This project consists in analyzing the timbre blend of some representative most popular songs along last 60 years: Billboard Hot 100's first positions of all weeks of the analysed years. The study focus the attention in ...
  • Multi-speaker Neural Vocoder 

    Barbany Mayor, Oriol (Universitat Politècnica de Catalunya, 2018-06)
    Treball Final de Grau
    Accés obert
    Deep learning has revolutionized almost every engineering branch over the past decades and have also been successfully applied to text-to-speech, where it yields state-of-the-art performance and overcomes classical approaches. ...
  • Neural Audio Generation for Speech Synthesis 

    Dorca Saez, Georgina (Universitat Politècnica de Catalunya, 2018-01)
    Treball Final de Grau
    Accés obert
    Recently, neural networks have become the state of the art for speech synthesis from raw text tasks and they are actually representing a powerful force in the industry. In this project, we present an end-to-end deep ...
  • Query by Humming 

    Tur Vallés, Pau (Universitat Politècnica de Catalunya, 2014-06)
    Treball Final de Grau
    Accés obert
    [ANGLÈS] In this thesis, a Query by Singing/Humming (QbSH) system has been developed. A QbSH system tries to retrieve information of a song given a melody recorded by the user. The system compares human queries with melodies ...
  • Query by Humming (Android app) 

    Siquier Penyafort, Marc (Universitat Politècnica de Catalunya, 2015-02)
    Treball Final de Grau
    Accés obert
    [ANGLÈS]In this thesis, a Query by Singing/Humming (QbSH) has been developed. A QbSH system tries to retrieve information of a song given a melody recorded by the user. It has been developed as a client/server system, where ...
  • Síntesis de voz aplicada a la traducción voz a voz 

    Agüero, Pablo Daniel (Universitat Politècnica de Catalunya, 2012-10-23)
    Tesi
    Accés obert
    In the field of speech technologies, text-to-speech conversion is the automatic generation of artificial voices that sound identical to a human voice when reading a text in loud speech. Inside a text-to-speech system, the ...
  • Síntesis de voz mediante Modelos Ocultos de Markov 

    Folgueira Bande, Ivan (Universitat Politècnica de Catalunya, 2008-11-27)
    Projecte/Treball Final de Carrera
    Accés obert