[pt] O crescente interesse por imitar o modelo que rege o processo cotidiano de comunicação humana através de maquinas tem se convertido em uma das áreas do conhecimento mais pesquisadas e de grande importância nas ultimas décadas. Esta área da tecnologia, conhecida como reconhecimento de voz, em como principal desafio desenvolver sistemas robustos que diminuam o ruído aditivo dos ambientes de onde o sinal de voz é adquirido, antes de que se esse sinal alimente os reconhecedores de voz. Por esta razão, este trabalho apresenta quatro formas diferentes de melhorar o desempenho do reconhecimento de voz contınua na presença de ruído aditivo, a saber: Wavelet Denoising e Subtração Espectral, para realce de fala e Mapeamento de Histogramas e Filtro com Redes Neurais, para compensação de atributos. Esses métodos são aplicados isoladamente e simultaneamente, afim de minimizar os desajustes causados pela inserção de ruído no sinal de voz. Alem dos métodos de robustez propostos, e devido ao fato de que os e conhecedores de voz dependem basicamente dos atributos de voz utilizados, examinam-se dois algoritmos de extração de atributos, MFCC e PNCC, através dos quais se representa o sinal de voz como uma sequência de vetores que contêm informação espectral de curtos períodos de tempo. Os métodos considerados são avaliados através de experimentos usando os software HTK e Matlab, e as bases de dados TIMIT (de vozes) e NOISEX-92 (de ruído). Finalmente, para obter os resultados experimentais, realizam-se dois tipos de testes. No primeiro caso, é avaliado um sistema de referência baseado unicamente em atributos MFCC e PNCC, mostrando como o sinal é fortemente degradado quando as razões sinal-ruıdo são menores. No segundo caso, o sistema de referência é combinado com os métodos de robustez aqui propostos, analisando-se comparativamente os resultados dos métodos quando agem isolada e simultaneamente. Constata-se que a mistura simultânea dos métodos nem sempre é mais atraente. Porem, em geral o melhor resultado é obtido combinando-se MAP com atributos PNCC. / [en] The increasing interest in imitating the model that controls the daily process of human communication trough machines has become one of the most researched areas of knowledge and of great importance in recent decades. This technological area known as voice recognition has as a main challenge to develop robust systems that reduce the noisy additive environment where the signal voice was acquired. For this reason, this work presents four different ways to improve the performance of continuous speech recognition in presence of additive noise, known as Wavelet Denoising and Spectral Subtraction for enhancement of voice, and Mapping of Histograms and Filter with Neural Networks to compensate for attributes. These methods are applied separately and simultaneously two by two, in order to minimize the imbalances caused by the inclusion of noise in voice signal. In addition to the proposed methods of robustness and due to the fact that voice recognizers depend mainly on the attributes voice used, two algorithms are examined for extracting attributes, MFCC, and PNCC, through which represents the voice signal as a sequence of vectors that contain spectral information for short periods of time. The considered methods are evaluated by experiments using the HTK and Matlab software, and databases of TIMIT (voice) and Noisex-92 (noise). Finally, for the experimental results, two types of tests were carried out. In the first case a reference system was assessed based on MFCC and PNCC attributes, only showing how the signal degrades strongly when signal-noise ratios are higher. In the second case, the reference system is combined with robustness methods proposed here, comparatively analyzing the results of the methods when they act alone and simultaneously. It is noted that simultaneous mix of methods is not always more attractive. However, in general, the best result is achieved by the combination of MAP with PNCC attributes.

Στην παρούσα εργασία επιχειρείται η εφαρμογή αλγορίθμων αποθορυβοποίησης σε σήματα μουσικής και η εξαγωγή συμπερασμάτων σχετικά με την απόδοση αυτών ανά μουσικό είδος. Η κύρια επιδίωξη είναι να αποσαφηνιστούν τα βασικά προβλήματα της ενίσχυσης ήχων και να παρουσιαστούν οι διάφοροι αλγόριθμοι που έχουν αναπτυχθεί για την επίλυση των προβλημάτων αυτών. Αρχικά γίνεται μία σύντομη εισαγωγή στις βασικές έννοιες πάνω στις οποίες δομείται η τεχνολογία ενίσχυσης ομιλίας. Στην συνέχεια εξετάζονται και αναλύονται αντιπροσωπευτικοί αλγόριθμοι από κάθε κατηγορία τεχνικών αποθορυβοποίησης, την κατηγορία φασματικής αφαίρεσης, την κατηγορία στατιστικών μοντέλων και αυτήν του υποχώρου. Για να μπορέσουμε να αξιολογήσουμε την απόδοση των παραπάνω αλγορίθμων χρησιμοποιούμε αντικειμενικές μετρήσεις ποιότητας, τα αποτελέσματα των οποίων μας δίνουν την δυνατότητα να συγκρίνουμε την απόδοση του κάθε αλγορίθμου. Με την χρήση τεσσάρων διαφορετικών μεθόδων αντικειμενικών μετρήσεων διεξάγουμε τα πειράματα εξάγοντας μια σειρά ενδεικτικών τιμών που μας δίνουν την ευχέρεια να συγκρίνουμε είτε τυχόν διαφοροποιήσεις στην απόδοση των αλγορίθμων της ίδιας κατηγορίας είτε διαφοροποιήσεις στο σύνολο των αλγορίθμων. Από την σύγκριση αυτή γίνεται εξαγωγή χρήσιμων συμπερασμάτων σχετικά με τον προσδιορισμό των παραμέτρων κάθε αλγορίθμου αλλά και με την καταλληλότητα του κάθε αλγορίθμου για συγκεκριμένες συνθήκες θορύβου και για συγκεκριμένο μουσικό είδος. / This thesis attempts to apply Noise Reduction algorithms to signals of music and draw conclusions concerning the performance of each algorithm for every musical genre. The main aims are to clarify the basic problems of sound enhancement and present the various algorithms developed for solving these problems. After a brief introduction to basic concepts on sound enhancement we examine and analyze various algorithms that have been proposed at times in the literature for speech enhancement. These algorithms can be divided into three main classes: spectral subtractive algorithms, statistical-model-based algorithms and subspace algorithms. In order to evaluate the performance of the above algorithms we use objective measures of quality, the results of which give us the opportunity to compare the performance of each algorithm. By using four different methods of objective measures to conduct the experiments we draw a set of values that facilitate us to make within-class algorithm comparisons and across-class algorithm comparisons. From these comparisons we can draw conclusions on the determination of parameters for each algorithm and the appropriateness of algorithms for specific noise conditions and music genre.