Sökning: "dictionary learning"

Visar resultat 1 - 5 av 7 avhandlingar innehållade orden dictionary learning.

  1. 1. Sparse Modeling of Grouped Line Spectra

    Författare :Ted Kronvall; Statistical Signal Processing Group; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; line spectra; parameter estimation; convex optimization; group-sparsity; block-sparsity; dictionary learning; ADMM; adaptive penalty; total variation; multi-pitch estimation; chroma; audio processing; TDOA; near-field localization; amplitude modulation;

    Sammanfattning : This licentiate thesis focuses on clustered parametric models for estimation of line spectra, when the spectral content of a signal source is assumed to exhibit some form of grouping. Different from previous parametric approaches, which generally require explicit knowledge of the model orders, this thesis exploits sparse modeling, where the orders are implicitly chosen. LÄS MER

  2. 2. Parameter Estimation - in sparsity we trust

    Författare :Johan Swärd; Statistical Signal Processing Group; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; TEKNIK OCH TEKNOLOGIER; NATURAL SCIENCES; ENGINEERING AND TECHNOLOGY; Parameter estimation; Sparse models; Convex optimization; Symbolic Periodicity; Alternating direction method of multipliers ADMM ; Covariance fitting; multi-pitch estimation problem; Off-grid estimation; Dictionary learning; Atomic norm; Sampling schemes;

    Sammanfattning : This thesis is based on nine papers, all concerned with parameter estimation. The thesis aims at solving problems related to real-world applications such as spectroscopy, DNA sequencing, and audio processing, using sparse modeling heuristics. LÄS MER

  3. 3. Unsupervised feature learning applied to condition monitoring

    Författare :Sergio Martín del Campo Barraza; Fredrik Sandin; Kjersti Engan; Luleå tekniska universitet; []

    Sammanfattning : Improving the reliability and efficiency of rotating machinery are central problems in many application domains, such as energy production and transportation. This requires efficient condition monitoring methods, including analytics needed to predict and detect faults and manage the high volume and velocity of data. LÄS MER

  4. 4. Speech Enhancement Using Nonnegative MatrixFactorization and Hidden Markov Models

    Författare :Nasser Mohammadiha; Arne Leijon; W. Bastiaan Kleijn; Cédric Févotte; KTH; []
    Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; Speech enhancement; noise reduction; nonnegative matrix factorization; hidden Markov model; probabilistic latent component analysis; online dictionary learning; super-Gaussian distribution; MMSE estimator; temporal dependencies; dynamic NMF;

    Sammanfattning : Reducing interference noise in a noisy speech recording has been a challenging task for many years yet has a variety of applications, for example, in handsfree mobile communications, in speech recognition, and in hearing aids. Traditional single-channel noise reduction schemes, such as Wiener filtering, do not work satisfactorily in the presence of non-stationary background noise. LÄS MER

  5. 5. Automated Text Analysis of Online Content in Marketing : Dictionray-Based Methods and Artificial Intelligence

    Författare :Christine Pitt; Esmail Salehi-Sangari; Julie Tinson; KTH; []
    Nyckelord :SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Automated text analysis; content analysis; artificial intelligence-based tools; dictionary-based tools; marketing focus activity ies ; creation; experience; Automatiserad textanalys; innehållsanalys; artificiella intelligens-baserade verktyg; ordbok-baserade verktyg; marknadsfokusaktivitet er ; skapande; erfarenhet; Industrial Economics and Management; Industriell ekonomi och organisation;

    Sammanfattning : Far more than products or services, words are the most fundamental element in the exchanges between sellers and buyers. Understanding the words that constitute the text that is created when sellers and buyers interact with each other is therefore critical for marketing decision makers. LÄS MER