Dissertations / Theses on the topic 'Speech filtering'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Speech filtering.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Ledoux, Christelle Michelle. "Robust speech filtering in impulsive noise environments." Thesis, Virginia Tech, 1999. http://hdl.handle.net/10919/46325.
Full textMaster of Science
Ramachandran, Ravi P. "Pitch filtering in adaptive predictive coding of speech." Thesis, McGill University, 1986. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=65345.
Full textKlein, Mark 1977. "Signal subspace speech enhancement with perceptual post-filtering." Thesis, McGill University, 2002. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=33975.
Full textThis thesis introduces the Enhanced Signal Subspace (ESS) system to mitigate the above problems. Based on a signal subspace framework, ESS has been designed to attenuate disturbances while minimizing audible distortion.
Artefacts are reduced by employing an auditory post-filter to smooth the enhanced speech spectra. This filter performs averaging in a manner that exploits the properties of the human auditory system. As such, distortion of the underlying speech signal is reduced.
Testing shows that listeners prefer the proposed algorithm to traditional signal subspace speech enhancement.
Chan, Dominic Sai Fan. "Speech production modelling based on glottal inverse filtering." Thesis, Imperial College London, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307161.
Full textLewine, Andrew (Andrew P. ). "Speech filtering for improving intelligibility in noisy transients." Thesis, Massachusetts Institute of Technology, 2011. http://hdl.handle.net/1721.1/66433.
Full textCataloged from PDF version of thesis.
Includes bibliographical references.
Hearing impairment is a problem that affects a large percentage of the population. Cochlear implants allow those with profound or total hearing loss to regain some hearing by stimulating auditory nerve fibers with implanted electrodes, in response to sound picked up by an external microphone. The signal processing chain from microphone input to stimulation output is an important factor in the overall speech intelligibility of the implant system. This thesis work improves on an existing ultra-low-power cochlear implant system by utilizing an improved noise and power efficient bandpass filter bank to implement a novel frequency-selective gain control algorithm capable of reducing, and in some cases removing, loud transient noises, thereby improving speech intelligibility. This gain control algorithm takes advantage of the inherent frequency-specific gain control afforded by the improved bandpass filter topology. This contribution makes an improvement to the existing state-of-the-art system in both power efficiency and performance.
by Andrew Lewine.
M.Eng.
Dubbin, Gregory. "Applying particle filtering to unsupervised part-of-speech induction." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:48caedb6-478f-4bb0-8ca7-975ee7fe5e38.
Full textPapanagiotou, Kyriakos. "Enhancement of body conducted speech from an ear microphone." Thesis, University of Southampton, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.289914.
Full textDarlington, David J. "The enhancement of noise-corrupted speech by sub-band adaptive filtering." Thesis, University of the West of Scotland, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.388213.
Full textHu, Rong. "Enhancement of adaptive de-correlation filtering separation model for robust speech recognition." Diss., Columbia, Mo. : University of Missouri-Columbia, 2007. http://hdl.handle.net/10355/4682.
Full textThe entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on September 25, 2007) Vita. Includes bibliographical references.
Mustiere, Frederic. "Particle filtering methods for the enhancement of speech corrupted by additive noise." Thesis, University of Ottawa (Canada), 2006. http://hdl.handle.net/10393/27398.
Full textWang, Yao Electrical Engineering & Telecommunications Faculty of Engineering UNSW. "Single channel speech enhancement based on perceptual temporal masking model." Awarded by:University of New South Wales. Electrical Engineering & Telecommunications, 2007. http://handle.unsw.edu.au/1959.4/40454.
Full textMa, Ning. "Speech enhancement algorithms using Kalman filtering and masking properties of human auditory systems." Thesis, University of Ottawa (Canada), 2005. http://hdl.handle.net/10393/29229.
Full textGransden, I. R. "High speed auditory analysis." Thesis, University of Sheffield, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.364247.
Full textGobl, Christer. "The Voice Source in Speech Communication - Production and Perception Experiments Involving Inverse Filtering and Synthesis." Doctoral thesis, KTH, Speech Transmission and Music Acoustics, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3665.
Full textThis thesis explores, through a number of production andperception studies, the nature of the voice source signal andhow it varies in spoken communication. Research is alsopresented that deals with the techniques and methodologies foranalysing and synthesising the voice source. The main analytictechnique involves interactive inverse filtering for obtainingthe source signal, which is then parameterised to permit thequantification of source characteristics. The parameterisationis carried by means of model matching, using the four-parameterLF model of differentiated glottal flow.
The first three analytic studies focus on segmental andsuprasegmental determinants of source variation. As part of theprosodic variation of utterances, focal stress shows for theglottal excitation an enhancement between the stressed voweland the surrounding consonants. At a segmental level, the voicesource characteristics of a vowel show potentially majordifferences as a function of the voiced/voiceless nature of anadjacent stop. Cross-language differences in the extent anddirectionality of the observed effects suggest differentunderlying control strategies in terms of the timing of thelaryngeal and supralaryngeal gestures, as well as in thelaryngeal tensions settings. Different classes of voicedconsonants also show differences in source characteristics:here the differences are likely to be passive consequences ofthe aerodynamic conditions that are inherent to the consonants.Two further analytic studies present voice source correlatesfor six different voice qualities as defined by Laver'sclassification system. Data from stressed and unstressedcontexts clearly show that the transformation from one voicequality to another does not simply involve global changes ofthe source parameters. As well as providing insights into theseaspects of speech production, the analytic studies providequantitative measures useful in technology applications,particularly in speech synthesis.
The perceptual experiments use the LF source implementationin the KLSYN88 synthesiser to test some of the analytic resultsand to harness them to explore the paralinguistic dimension ofspeech communication. A study of the perceptual salience ofdifferent parameters associated with breathy voice indicatesthat the source spectral slope is critically important andthat, surprisingly, aspiration noise contributes relativelylittle. Further perceptual tests using stimuli with differentvoice qualities explore the mapping between voice quality andits paralinguistic function of expressing emotion, mood andattitude. The results of these studies highlight the crucialrole of voice quality in expressing affect as well as providingpointers to how it combines withf0for this purpose.
The last section of the thesis focuses on the techniquesused for the analysis and synthesis of the source. Asemi-automatic method for inverse filtering is presented, whichis novel in that it optimises the inverse filter by exploitingthe knowledge that is typically used by the experimenter whencarrying out manual interactive inverse filtering. A furtherstudy looks at the properties of the modified LF model in theKLSYN88 synthesiser: it highlights how it differs from thestandard LF model and discusses the implications forsynthesising the glottal source signal from LF model data.Effective and robust source parameterisation for the analysisof voice quality is the topic of the final paper: theeffectiveness of global, amplitude-based, source parameters isexamined across speech tokens with large differences inf0. Additional amplitude-based parameters areproposed to enable a more detailed characterisation of theglottal pulse.
Keywords:Voice source dynamics, glottal sourceparameters, source-filter interaction, voice quality,phonation, perception, affect, emotion, mood, attitude,paralinguistic, inverse filtering, knowledge-based, formantsynthesis, LF model, fundamental frequency,f0.
Courtis, N. J. "Some aspects of speech intelligibility enhancement with particular regard to adaptive filtering and room acoustics." Thesis, University of Hertfordshire, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.356313.
Full textOzbek, Ibrahim Yucel. "Dynamic System Modeling And State Estimation For Speech Signal." Phd thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/3/12611777/index.pdf.
Full textGaussian mixture model (GMM) regression based inversion and Jump Markov Linear System (JMLS) based inversion. GMM regression based inversion method involves modeling audio (and /or visual) and articulatory data as a joint Gaussian mixture model. The conditional expectation of this distribution gives the desired articulatory estimate. In this method, we examine the usefulness of the combination of various acoustic features and effectiveness of various types of fusion techniques in combination with audiovisual features. Also, we propose dynamic smoothing methods to smooth articulatory trajectories. The performance of the proposed algorithm is illustrated and compared with conventional algorithms. JMLS inversion involves tying the acoustic (and/or visual) spaces and articulatory space via multiple state space representations. In this way, the articulatory inversion problem is converted into the state estimation problem where the audiovisual data are considered as measurements and articulatory positions are state variables. The proposed inversion method first learns the parameter set of the state space model via an expectation maximization (EM) based algorithm and the state estimation is handled via interactive multiple model (IMM) filter/smoother.
Abel, Andrew. "Towards an intelligent fuzzy based multimodal two stage speech enhancement system." Thesis, University of Stirling, 2013. http://hdl.handle.net/1893/15989.
Full textNallamilli, Sai Chandra Sekhar Reddy, and Nihanth Kandi. "Detection of Human Emotion from Noise Speech." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-19610.
Full textThüne, Philipp [Verfasser], Gerald [Gutachter] Enzner, and Peter [Gutachter] Jax. "Advances in blind multichannel Wiener filtering of noisy speech / Philipp Thüne ; Gutachter: Gerald Enzner, Peter Jax ; Fakultät für Elektrotechnik und Informationstechnik." Bochum : Ruhr-Universität Bochum, 2017. http://d-nb.info/1150509546/34.
Full textTorres, Juan Félix. "Estimation of glottal source features from the spectral envelope of the acoustic speech signal." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/34736.
Full textWu, Mingyang. "Pitch tracking and speech enhancement in noisy and reverberant environments." Columbus, Ohio : Ohio State University, 2003. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1064341479.
Full textTitle from first page of PDF file. Document formatted into pages; contains xvi, 149 p.; also includes graphics. Includes abstract and vita. Advisor: DeLiang Wang, Dept. of Computer and Information Science. Includes bibliographical references (p. 136-149).
Roman, Nicoleta. "Auditory-based algorithms for sound segregation in multisource and reverberant environments." Connect to resource, 2005. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1124370749.
Full textTitle from first page of PDF file. Document formatted into pages; contains i-xxii, xx-xxi, 183 p.; also includes graphics. Includes bibliographical references (p. 171-183). Available online via OhioLINK's ETD Center
Tan, Ke. "Convolutional and recurrent neural networks for real-time speech separation in the complex domain." The Ohio State University, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=osu1626983471600193.
Full textNeville, Katrina Lee, and katrina neville@rmit edu au. "Channel Compensation for Speaker Recognition Systems." RMIT University. Electrical and Computer Engineering, 2007. http://adt.lib.rmit.edu.au/adt/public/adt-VIT20080514.093453.
Full textDeivard, Johannes. "How accuracy of estimated glottal flow waveforms affects spoofed speech detection performance." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-48414.
Full textAl-saqaf, Walid. "Breaking digital firewalls : analyzing internet censorship and circumvention in the arab world." Doctoral thesis, Örebro universitet, Institutionen för humaniora, utbildnings- och samhällsvetenskap, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-34596.
Full textMotlagh, Zadeh Lina. "Developing a digits in noise screening test with higher sensitivity to high-frequency hearing loss." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1552378973670023.
Full textHoudek, Miroslav. "Rozpoznání emočního stavu člověka z řeči." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-218117.
Full textRao, Peddi Srinivas, and Vallabhaneni Sreelatha. "Implementation and Evaluation of Spectral Subtraction with Minimum Statistics using WOLA and FFT Modulated Filter Banks." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2906.
Full textMatos, Adriano Nogueira. "Extração de características do sinal de voz utilizando análise fatorial verdadeira." Universidade Federal do Amazonas, 2008. http://tede.ufam.edu.br/handle/tede/2959.
Full textCoordenação de Aperfeiçoamento de Pessoal de Nível Superior
Digital processing of speech signal is applied in several computer applications, which the major ones are the following: Recognition, synthesis and coding of speech. All these applications require the amount of data in the acoustic signal to be reduced, in order to allow processing by a computer device. The feature extraction of speech signal, that is the goal of this study, performs this action. The features extracted should well depict the speech signal and should have no redundancy, in order to increase the performance of the systems using them. The feature extraction Mel Frequency Cepstral Coefficients (MFCC) method partially fulfills these requirements, but it is seriously damaged when noise signal is acting. The appliance of the statistical method of Factorial Analysis is intended to filter the noise components from the speech. The results of the experiments performed in this work shows that this is a competitive method, especially when used to generate acoustic models in severe noise conditions.
O processamento digital do sinal de voz é empregado em diversas aplicações computacionais, das quais as principais são: Reconhecimento, síntese e codificação da fala. Todas estas aplicações requerem que ocorra redução da quantidade de informações da onda acústica, de maneira a permitir o processamento por um computador. O processo de extração de características do sinal de voz, objeto de estudo deste trabalho, realiza esta tarefa. As características extraídas devem caracterizar o sinal de voz e não conter redundância, de forma a maximizar o desempenho dos sistemas que as utilizem. O método MFCC (Mel Frequency Cepstral Coefficients) de extração de características cumpre parcialmente esses requisitos, mas é seriamente degradado sob a incidência de ruído. A aplicação do método estatístico de Análise Fatorial objetiva filtrar o sinal de ruído das locuções. Os resultados obtidos dos experimentos realizados indicam a competitividade deste método, especialmente quando usado na geração dos modelos acústicos robustos em condições de ruído severo.
Crespo, Cuaresma Jesus, and Martin Feldkircher. "Spatial Filtering, Model Uncertainty and the Speed of Income Convergence in Europe." Wiley, 2013. http://dx.doi.org/10.1002/jae.2277.
Full textOlugbenga, Olubodun. "High speed optical phase modulated signaling with offset filtering in a 50 GHz grid." Thesis, Swansea University, 2011. https://cronfa.swan.ac.uk/Record/cronfa42896.
Full textHawkins, Mikhel E. "High speed target tracking using Kalman filter and partial window imaging." Thesis, Georgia Institute of Technology, 2002. http://hdl.handle.net/1853/16709.
Full textSturmel, Nicolas. "Analyse de la qualité vocale appliquée à la parole expressive." Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00591638.
Full textHollis, Timothy Mowry. "Circuit and Modeling Solutions for High-Speed Chip-to-Chip Communication." BYU ScholarsArchive, 2007. https://scholarsarchive.byu.edu/etd/1067.
Full textJemâa, Imen. "Suivi de formants par analyse en multirésolution." Thesis, Université de Lorraine, 2013. http://www.theses.fr/2013LORR0026/document.
Full textOur research work presented in this thesis aims the optimization of the performance of formant tracking algorithms. We began by analyzing different existing techniques used in the automatic formant tracking. This analysis showed that the automatic formant estimation remains difficult despite the use of complex techniques. For the non-availability of database as reference in Arabic, we have developed a phonetically balanced corpus in Arabic while developing a manual phonetic and formant tracking labeling. Then we presented our two new automatic formant tracking approaches which are based on the estimation of Fourier ridges (local maxima of spectrogram) or wavelet ridges (local maxima of scalogram) using as a tracking constraint the calculation of center of gravity of a set of candidate frequencies for each formant, while the second tracking approach is based on dynamic programming combined with Kalman filtering. Finally, we made an exploratory study using manually labeled corpus as a reference to quantify our two new approaches compared to other automatic formant tracking methods. We tested the first approach based on wavelet ridges detection, using the calculation of the center of gravity on synthetic signals and then on real signals issued from our database by testing three types of complex wavelets (CMOR, SHAN and FBSP). Following these tests, it appears that formant tracking and scalogram resolution given by CMOR and FBSP wavelets are better than the SHAN wavelet. To quantitatively evaluate our two approaches, we calculated the absolute difference average and standard deviation. We made several tests with different speakers (male and female) on various long and short vowels and continuous speech signals issued from our database using it as a reference. The formant tracking results are compared to those of Fourier ridges method calculating the center of gravity, LPC analysis combined with filter banks method of Kamran.M and LPC analysis integrated in Praat software. According to the results of the vowels / a / and / A /, we found that formant tracking by the method with wavelet CMOR is generally better than other methods. Therefore, this method provides a correct formant tracking (F1, F2 and F3) and closer to the reference. The results of Fourier and wavelet methods are very similar in some cases since both have fewer errors than the method Praat. These results are proven for the five male speakers which is not the case for the other vowels where there are some errors which are present sometimes in F2 and sometimes in F3. According to the results obtained on continuous speech, we found that in the case of male speakers, the result of both approaches are particularly better than those of Kamran.M method and those of Praat even if they are often few errors in F3. They are also very close to the Fourier ridges method using the calculation of center of gravity. The results obtained in the case of female speakers confirm the trend observed over the male speakers
Vatte, Madhu Latha Reddy. "Readout Circuitry for a Logarithmic CMOS Active Pixel Sensor That Facilities High Speed Image Processing." University of Akron / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=akron1278549382.
Full textLai, Ying-Chun. "A Development of a Common-Mode FilterUsing an EBG Structure in High Speed SerialLinks." Thesis, KTH, Elektroteknisk teori och konstruktion, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-104986.
Full textHamlet, Sean Michael. "COMPARING ACOUSTIC GLOTTAL FEATURE EXTRACTION METHODS WITH SIMULTANEOUSLY RECORDED HIGH-SPEED VIDEO FEATURES FOR CLINICALLY OBTAINED DATA." UKnowledge, 2012. http://uknowledge.uky.edu/ece_etds/12.
Full textPokora, C. D. "Spatio-temporal correlations of jets using high-speed particle image velocimetry." Thesis, Loughborough University, 2009. https://dspace.lboro.ac.uk/2134/13185.
Full textChenais, Patrick. "Une carte de traitement et de reconnaissance de la parole : etude de cibles acoustiques." Toulouse 3, 1987. http://www.theses.fr/1987TOU30009.
Full textCaliskan, Hakan. "Modeling And Experimental Evaluation Of Variable Speed Pump And Valve Controlled Hydraulic Servo Drives." Master's thesis, METU, 2009. http://etd.lib.metu.edu.tr/upload/3/12611090/index.pdf.
Full textwhereas in the pump controlled system, two variable speed pumps driven by servomotors regulate the flow rate according to the needs of the system, thus eliminating the valve losses. To understand the dynamic behaviors of two systems, the order of the differential equations defining the system dynamics of the both systems are reduced by using the fact that the dynamic pressure changes in the hydraulic cylinder chambers become linearly dependent on leakage coefficients and cylinder chamber volumes above and below some prescribed cut off frequencies. Thus the open loop speed response of the pump controlled and valve controlled systems are defined by v second order transfer functions. The two systems are modeled in MATLAB Simulink environment and the assumptions are validated. For the position control of the single rod hydraulic actuator, a linear state feedback control scheme is applied. Its state feedback gains are determined by using the linear and linearized reduced order dynamic system equations. A linear Kalman filter for pump controlled system and an unscented Kalman filter for valve controlled system are designed for estimation and filtering purposes. The dynamic performances of both systems are investigated on an experimental test set up developed by conducting open loop and closed loop frequency response and step response tests. MATLAB Real Time Windows Target (RTWT) module is used in the tests for application purposes.
Buyukkeles, Umit. "Improved Torque And Speed Control Performance In A Vector-controlled Pwm-vsi Fed Surface-mounted Pmsm Drive With Conventional P-i Controllers." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614294/index.pdf.
Full textOlsson, Rickard. "Signal processing and high speed imaging as monitoring tools for pulsed laser welding." Licentiate thesis, Luleå tekniska universitet, Produkt- och produktionsutveckling, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-26555.
Full textGodkänd; 2009; 20091103 (ricols); LICENTIATSEMINARIUM Ämnesområde: Produktionsutveckling/Manufacturing Systems Engineering Examinator: Professor Alexander Kaplan, Luleå tekniska universitet Tid: Onsdag den 16 december 2009 kl 13.00 Plats: E 232, Luleå tekniska universitet
Bartholomew, David Ray. "Design of a High Speed Mixed Signal CMOS Mutliplying Circuit." Diss., CLICK HERE for online access, 2004. http://contentdm.lib.byu.edu/ETD/image/etd362.pdf.
Full textKučera, Jan. "Filtrace paketů ve 100 Gb sítích." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2016. http://www.nusl.cz/ntk/nusl-255423.
Full textIspir, Mehmet. "Design Of Moving Target Indication Filters With Non-uniform Pulse Repetition Intervals." Master's thesis, METU, 2013. http://etd.lib.metu.edu.tr/upload/12615361/index.pdf.
Full textTörnquist, Martin. "Investigation of rotational velocity sensors." Thesis, Linköping University, Department of Electrical Engineering, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-15904.
Full textTo improve the speed measurement of construction equipment, different sensor technologies have been investigated. Many of these sensor technologies are very interesting but to keep the extent of the thesis only two was chosen for testing, magnetic absolute angle sensors using Hall and GMR technology, to investigate if those are a valid replacement for the current measurement system that is using a passive sensor. Tests show that these sensors are capable of speed measurement, but because of noisy angle estimates they need filtering for good speed computation. This filtering introduces a large time delay that is of significance for the quality of the estimate. A Kalman filter has been implemented in an attempt to lower the time delays but since only a very simple model has been used it does not give any improvements over ordinary low pass filtering. For these sensors the mounting tolerance is of great interest. For best performance the offset between the sensor and magnet centres need to be kept small for both sensors. This is due to a non-linearity effect this causes. The distance between the sensors and the magnet is not critical for linearity issues, but only for the quality of the signal, where it might drop out when the distance is too large. This is where the sensor using GMR technology stands out. Compared to the Hall technology sensor, the GMR sensor can handle distances that are more than 10 times larger. The conclusion is that these sensors can be a valid replacement of the current measurement system. They will introduce more functionality with the capability of detecting rotational direction and zero velocity. In an application with more than one sensor they can also be used for more purposes, like detecting slip in clutches etc. Depending on the application, the time delays may not be critical, else more work need to be done to improve the estimate, e.g. with a more advanced model for the Kalman filter.
Silva, Cristiane Cristina Sousa da. "UM ALGORITMO TIPO RLS BASEADO EM SUPERFÍCIES NÃO QUADRÁTICAS." Universidade Federal do Maranhão, 2013. http://tedebc.ufma.br:8080/jspui/handle/tede/550.
Full textCoordenação de Aperfeiçoamento de Pessoal de Nível Superior
In adaptive filtering many adaptive filter are based on the mean square error method (MSE). These filters were developed to improve convergence spedd with a lower misadjustment. The least mean square (LMS) and the recursive least square (RLS) algorithms have been the hallmark of adaptive filtering. In this work we develop adaptive algorithms based on the even powers of the error inspired in the recursive lest square (RLS) algorithm. Namely recursive nom quadratic (RNQ) algorithm. The ideas is based on Widrow s least mean square fourth (LMF) algorithm. Fisrt we derive equations based on a singal even power of the error in order to obtain criterions that guarantee convergence. We also determine equations that measure the misadjustment and the time constant of the adaptive process of the RNQ algorithm. We work also, toward making the algorithm less sensitive to the size of the error in na alternative direction, by proposing a cost function which is a sum of the even powers of the error. This second approach bring the error explicitly to the RLS algorithm formulation by proposing a new cost function that preserves the measnsquare-error (MSE) solution, but allows for the exploitation of higher order moments of the error to speedup the converge of the algorithm. The main goal this work is to create form first principles (new cost functions ) a mechanism to include instantaneous error information in the RLS algorithm, make it track better, and allow for the design of the forgetting factor. As we will see the key aspecto of our approach is to include the error in the Kalman gain that effectively controls the speed of adaptation of the RLS algorithm.
Em filtragem adaptativa, vários filtros são baseados no método do erro quadrático médio (do inglês, MSE- mean squared error ) e muitos desses foram desenvolvidos para obter uma convergência rápida com um menos desajuste. Os algoritmos mínimos quadrático médio (do inglês, LMS- least mean square ) e mínimos quadrados recursivos (do inglês, RLS- recursive least square ) foram um marco em filtragem adaptativa. Nesse trabalho apresentamos o desenvolvimento de uma família de algoritmos adaptativos baseados nas potências pares do erro, inspirado na dedução do algoritmo RLS padrão. Chamaremos esses novos algoritmos de recursivo não-quadrático (RNQ). A ideia básica é baseada na função de custo apresentada por Widrow no algoritmo mínimo quarto médio ( do inglês, LMF least mean square fourth). Inicialmente derivamos equações baseados em uma potência par do erro para obter critérios que garantam a convergência. Determinamos também, equações que definem o desajuste e o tempo de aprendizagem do processo de adaptação do algoritmo RNQ baseado em potência para arbitrária. Trabalhamos também, no sentido de tornar o algoritmo menos sensível ao tamanho do erro numa direção alternativa, propondo uma função de custo baseado na soma das potências pares do erro. Essa segunda abordagem torna explícito o papel do erro na formulação do RLS ao propor uma nova função de custo que preserve a solução MSE, mas permite a utilização dos momentos de alta ordem do erro para aumentar a velocidade de convergência do algoritmo. O principal objetivo do nosso trabalho é criar a partir dos primeiros princípios (novas funções de custo) um mecanismo para incluir informações de erro instantâneo no algoritmo RLS e torná-lo um seguidor melhor. Assim, o aspecto-chave dessa nova abordagem é incluir o erro no ganho de Kalman que controla efetivamente a velocidade de adaptação do algoritmo de RLS.
Hodaň, David. "Možnosti akcelerace symbolické regrese pomocí kartézského genetického programování." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2019. http://www.nusl.cz/ntk/nusl-403198.
Full text