Matches in SemOpenAlex for { <https://semopenalex.org/work/W114328863> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W114328863 abstract "Statistical signal processing has been very successful. We proposed novel probabilistic models and developed efficient algorithms for two important problems: speech enhancement and source separation.Part I focused on the speech enhancement. We developed two models with efficient algorithms. The first one assumed a Gaussian Mixture Model (GMM) in the log-spectral domain for speech prior which was trained by expectation maximization (EM) algorithm. Three approximations were employed to enhance the computational efficiency. The Laplace method estimated the signal by computing the mode of the posterior distribution, either in the frequency domain or in the log-spectrum domain. The Gaussian approximation converted the GMM in the log-spectrum domain into a GMM in the frequency domain by minimizing the KL-divergency. It provided an efficient gain and noise spectrum estimation with the EM algorithm. The second one used a Gaussian scale mixture model (GSMM) as speech prior. This model specified a stochastic dependency between the log-spectra and the frequency components which can be estimated simultaneously with GSMM. The algorithms for training the model and signal estimation were developed. All these algorithms were evaluated by applying them to enhance the speeches corrupted by the speech shaped noise (SSN). The experimental results demonstrated that the proposed algorithms improved the signal-to-noise ratio and lowered the word recognition error rate.In part II, a novel probabilistic framework based on Independent Vector Analysis (IVA) was proposed to separate the convolutive mixture of sources. IVA assumed a multidimensional GMM for the source priors. The joint modeling of all frequency bins originating from the same source prevented the permutation disorder that associated with independent component analysis (ICA). The GMM source priors could adapt to the statistics of the sources and enable IVA to separate different type of signals. We developed EM algorithms for both the noiseless case and noisy case. For noiseless case, an online algorithm was developed to handle non-stationary environments. For noisy case, noise reduction was achieved together with the separation processes. The algorithms were evaluated by applying them to separate the mixtures of speech and music. The experimental results showed improved performance over other algorithms." @default.
- W114328863 created "2016-06-24" @default.
- W114328863 creator A5036939761 @default.
- W114328863 creator A5044141636 @default.
- W114328863 creator A5079550600 @default.
- W114328863 date "2008-01-01" @default.
- W114328863 modified "2023-09-23" @default.
- W114328863 title "Speech enhancement and source separation using probabilistic models" @default.
- W114328863 hasPublicationYear "2008" @default.
- W114328863 type Work @default.
- W114328863 sameAs 114328863 @default.
- W114328863 citedByCount "0" @default.
- W114328863 crossrefType "journal-article" @default.
- W114328863 hasAuthorship W114328863A5036939761 @default.
- W114328863 hasAuthorship W114328863A5044141636 @default.
- W114328863 hasAuthorship W114328863A5079550600 @default.
- W114328863 hasConcept C105795698 @default.
- W114328863 hasConcept C11413529 @default.
- W114328863 hasConcept C114289077 @default.
- W114328863 hasConcept C115961682 @default.
- W114328863 hasConcept C121332964 @default.
- W114328863 hasConcept C153180895 @default.
- W114328863 hasConcept C154945302 @default.
- W114328863 hasConcept C163294075 @default.
- W114328863 hasConcept C163716315 @default.
- W114328863 hasConcept C182081679 @default.
- W114328863 hasConcept C19118579 @default.
- W114328863 hasConcept C2776182073 @default.
- W114328863 hasConcept C28490314 @default.
- W114328863 hasConcept C31972630 @default.
- W114328863 hasConcept C33923547 @default.
- W114328863 hasConcept C41008148 @default.
- W114328863 hasConcept C49781872 @default.
- W114328863 hasConcept C49937458 @default.
- W114328863 hasConcept C61224824 @default.
- W114328863 hasConcept C62520636 @default.
- W114328863 hasConcept C99498987 @default.
- W114328863 hasConceptScore W114328863C105795698 @default.
- W114328863 hasConceptScore W114328863C11413529 @default.
- W114328863 hasConceptScore W114328863C114289077 @default.
- W114328863 hasConceptScore W114328863C115961682 @default.
- W114328863 hasConceptScore W114328863C121332964 @default.
- W114328863 hasConceptScore W114328863C153180895 @default.
- W114328863 hasConceptScore W114328863C154945302 @default.
- W114328863 hasConceptScore W114328863C163294075 @default.
- W114328863 hasConceptScore W114328863C163716315 @default.
- W114328863 hasConceptScore W114328863C182081679 @default.
- W114328863 hasConceptScore W114328863C19118579 @default.
- W114328863 hasConceptScore W114328863C2776182073 @default.
- W114328863 hasConceptScore W114328863C28490314 @default.
- W114328863 hasConceptScore W114328863C31972630 @default.
- W114328863 hasConceptScore W114328863C33923547 @default.
- W114328863 hasConceptScore W114328863C41008148 @default.
- W114328863 hasConceptScore W114328863C49781872 @default.
- W114328863 hasConceptScore W114328863C49937458 @default.
- W114328863 hasConceptScore W114328863C61224824 @default.
- W114328863 hasConceptScore W114328863C62520636 @default.
- W114328863 hasConceptScore W114328863C99498987 @default.
- W114328863 hasOpenAccess W114328863 @default.
- W114328863 hasRelatedWork W1598872146 @default.
- W114328863 hasRelatedWork W1805204942 @default.
- W114328863 hasRelatedWork W1947708735 @default.
- W114328863 hasRelatedWork W1973729935 @default.
- W114328863 hasRelatedWork W1977775600 @default.
- W114328863 hasRelatedWork W2079918934 @default.
- W114328863 hasRelatedWork W2142230486 @default.
- W114328863 hasRelatedWork W2288558552 @default.
- W114328863 hasRelatedWork W2562157918 @default.
- W114328863 hasRelatedWork W2575932760 @default.
- W114328863 hasRelatedWork W2743121184 @default.
- W114328863 hasRelatedWork W2775997803 @default.
- W114328863 hasRelatedWork W2800349810 @default.
- W114328863 hasRelatedWork W2887112268 @default.
- W114328863 hasRelatedWork W2922004249 @default.
- W114328863 hasRelatedWork W2979850772 @default.
- W114328863 hasRelatedWork W3086138182 @default.
- W114328863 hasRelatedWork W3109458322 @default.
- W114328863 hasRelatedWork W3114228145 @default.
- W114328863 hasRelatedWork W56422295 @default.
- W114328863 isParatext "false" @default.
- W114328863 isRetracted "false" @default.
- W114328863 magId "114328863" @default.
- W114328863 workType "article" @default.