FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1569589182> ?p ?o ?g. }

• W1569589182 abstract "When building a pattern recognition system, we primarily deal with stochastic signals such as speech, image, video, and so forth. Often, a stochastic signal is ideally of a one-vector form so that it appears as a single data point in a possibly high-dimensional representational space, as the majority of pattern recognition algorithms by design handle stochastic signals having a one-vector representation. More importantly, a one-vector representation naturally allows for optimal distance metric learning from the data, which generally accounts for significant performance increases in many pattern recognition tasks. This is motivated and demonstrated by our work on semi-supervised speaker clustering, where a speech utterance is represented by a Gaussian mixture model (GMM) mean supervector formed based on the component means of a GMM that is adapted from a universal background model (UBM) which encodes our prior knowledge of speakers in general. Combined with a novel distance metric learning technique that we propose, namely linear spherical discriminant analysis, which performs discriminant analysis in the cosine space, the GMM mean supervector representation of utterances leads to the state-of-the-art speaker clustering performance. Noting that the main criticism of the GMM mean supervector representation is that it assumes independent and identically distributed feature vectors, which is far from true in practice, we propose a novel one-vector representation of stochastic signals based on adapted ergodic hidden Markov models (HMMs) and a novel one-vector representation of stochastic signals based on adapted left-to-right HMMs. In these one-vector representations, a single vector is constructed based on a transformation of the parameters of an HMM that is adapted from a UBM by various controllable degrees, where the transformation is mathematically derived based on an upper bound approximation of the Kullback-Leibler divergence rate between two adapted HMMs. These one-vector representations possess a set of very attractive properties and are rather generic in nature, so they can be used with various types of stochastic signals (e.g. speech, image, video, etc.) and applied to a broad range of pattern recognition tasks (e.g. classification, regression, etc.). In addition, we propose a general framework for one-vector representations of stochastic signals for pattern recognition, of which the proposed one-vector representations based on adapted ergodic HMMs and adapted left-to-right HMMs respectively are two special cases. The general framework can serve as a unified and principled guide for constructing “the best” one-vector representations of stochastic signals of various types and for various pattern recognition tasks. Based on different types of underlying statistical models carefully and cleverly chosen to best fit the nature of the stochastic signals, “the best” one-vector representations of the stochastic signals may be constructed by a possibly nonlinear transformation of the parameters of the underlying statistical models which are learned from the stochastic signals, where the transformation may be mathematically derived from a properly chosen distance measure between two statistical models that has an elegant root in the Kullback-Leibler theory.Since most work in this dissertation is based on HMMs, we contribute to this fascinating tool via proposing a new maximum likelihood learning algorithm for HMMs, which we refer to as the boosting Baum-Welch algorithm. In the proposed boosting Baum-Welch algorithm, we formulate the HMM learning problem as an incremental optimization procedure which performs a sequential gradient descent search on a loss functional for a good fit in an inner product function space. The boosting Baum-Welch algorithm can serve as an alternative maximum likelihood learning algorithm for HMMs to the traditional Baum-Welch or expectation-maximization (EM) algorithm,and a preferred method for use in situations where there is insufficient training data available. Compared to the traditional Baum-Welch or EM algorithm, the boosting Baum-Welch algorithm is less susceptible to the over-fitting problem (known as a general property of maximum likelihood estimation techniques) in that the boosting Baum-Welch algorithm has a tendency to produce a “large margin” effect." @default.
• W1569589182 created "2016-06-24" @default.
• W1569589182 creator A5008831111 @default.
• W1569589182 creator A5030898980 @default.
• W1569589182 date "2010-01-01" @default.
• W1569589182 modified "2023-09-24" @default.
• W1569589182 title "One-vector representations of stochastic signals for pattern recognition" @default.
• W1569589182 cites W131248265 @default.
• W1569589182 cites W1480865305 @default.
• W1569589182 cites W1483662103 @default.
• W1569589182 cites W1502693945 @default.
• W1569589182 cites W1502955768 @default.
• W1569589182 cites W1508165687 @default.
• W1569589182 cites W1540596182 @default.
• W1569589182 cites W1544935352 @default.
• W1569589182 cites W1546503963 @default.
• W1569589182 cites W1554663460 @default.
• W1569589182 cites W1556474518 @default.
• W1569589182 cites W1560013842 @default.
• W1569589182 cites W1574901103 @default.
• W1569589182 cites W1578352865 @default.
• W1569589182 cites W1582821637 @default.
• W1569589182 cites W1663973292 @default.
• W1569589182 cites W1668904664 @default.
• W1569589182 cites W174669002 @default.
• W1569589182 cites W1790954942 @default.
• W1569589182 cites W181056519 @default.
• W1569589182 cites W1844030040 @default.
• W1569589182 cites W1871667158 @default.
• W1569589182 cites W1874027545 @default.
• W1569589182 cites W1880262756 @default.
• W1569589182 cites W1924689489 @default.
• W1569589182 cites W1953949349 @default.
• W1569589182 cites W1965555277 @default.
• W1569589182 cites W1967475838 @default.
• W1569589182 cites W1971784203 @default.
• W1569589182 cites W1975846642 @default.
• W1569589182 cites W1988790447 @default.
• W1569589182 cites W1997011019 @default.
• W1569589182 cites W2011430131 @default.
• W1569589182 cites W2013073424 @default.
• W1569589182 cites W2015245929 @default.
• W1569589182 cites W2020144989 @default.
• W1569589182 cites W2021982596 @default.
• W1569589182 cites W2024581784 @default.
• W1569589182 cites W2024600147 @default.
• W1569589182 cites W2024932073 @default.
• W1569589182 cites W2033773055 @default.
• W1569589182 cites W2041823554 @default.
• W1569589182 cites W2049633694 @default.
• W1569589182 cites W2064218608 @default.
• W1569589182 cites W2070534370 @default.
• W1569589182 cites W2086699924 @default.
• W1569589182 cites W2090861223 @default.
• W1569589182 cites W2097527229 @default.
• W1569589182 cites W2098693229 @default.
• W1569589182 cites W2099111195 @default.
• W1569589182 cites W2100969003 @default.
• W1569589182 cites W2101724615 @default.
• W1569589182 cites W2102331633 @default.
• W1569589182 cites W2103250033 @default.
• W1569589182 cites W2105080323 @default.
• W1569589182 cites W2106905947 @default.
• W1569589182 cites W2107528709 @default.
• W1569589182 cites W2107617395 @default.
• W1569589182 cites W2110530876 @default.
• W1569589182 cites W2111926505 @default.
• W1569589182 cites W2112634534 @default.
• W1569589182 cites W2119601766 @default.
• W1569589182 cites W2121407732 @default.
• W1569589182 cites W2121415728 @default.
• W1569589182 cites W2121805075 @default.
• W1569589182 cites W2125838338 @default.
• W1569589182 cites W2127218421 @default.
• W1569589182 cites W2127409454 @default.
• W1569589182 cites W2127936525 @default.
• W1569589182 cites W2132303541 @default.
• W1569589182 cites W2135188079 @default.
• W1569589182 cites W2135346934 @default.
• W1569589182 cites W2135623468 @default.
• W1569589182 cites W2136573752 @default.
• W1569589182 cites W2137306662 @default.
• W1569589182 cites W2137639365 @default.
• W1569589182 cites W2138243884 @default.
• W1569589182 cites W2140797123 @default.
• W1569589182 cites W2141262306 @default.
• W1569589182 cites W2142384583 @default.
• W1569589182 cites W2146871184 @default.
• W1569589182 cites W2147097131 @default.
• W1569589182 cites W2147147599 @default.
• W1569589182 cites W2147157320 @default.
• W1569589182 cites W2150260301 @default.
• W1569589182 cites W2151103935 @default.
• W1569589182 cites W2152321560 @default.
• W1569589182 cites W2154421872 @default.
• W1569589182 cites W2154872931 @default.
• W1569589182 cites W2156909104 @default.
• W1569589182 cites W2159017231 @default.
• W1569589182 cites W2159591770 @default.
• W1569589182 cites W2161939451 @default.

• next