FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022798421> ?p ?o ?g. }

• W2022798421 endingPage "1754" @default.
• W2022798421 startingPage "1742" @default.
• W2022798421 abstract "Robustness against noise and interfering audio signals is one of the challenges in speech recognition and audio analysis technology. One avenue to approach this challenge is single-channel multiple-source modeling. Factorial hidden Markov models (FHMMs) are capable of modeling acoustic scenes with multiple sources interacting over time. While these models reach good performance on specific tasks, there are still serious limitations restricting the applicability in many domains. In this paper, we generalize these models and enhance their applicability. In particular, we develop an EM-like iterative adaptation framework which is capable to adapt the model parameters to the specific situation (e.g. actual speakers, gain, acoustic channel, etc.) using only speech mixture data. Currently, source-specific data is required to learn the model. Inference in FHMMs is an essential ingredient for adaptation. We develop efficient approaches based on observation likelihood pruning. Both adaptation and efficient inference are empirically evaluated for the task of multipitch tracking using the GRID corpus." @default.
• W2022798421 created "2016-06-24" @default.
• W2022798421 creator A5015798259 @default.
• W2022798421 creator A5079103786 @default.
• W2022798421 date "2013-08-01" @default.
• W2022798421 modified "2023-10-16" @default.
• W2022798421 title "Model-Based Multiple Pitch Tracking Using Factorial HMMs: Model Adaptation and Inference" @default.
• W2022798421 cites W1528056001 @default.
• W2022798421 cites W1574263887 @default.
• W2022798421 cites W1800365115 @default.
• W2022798421 cites W1902027874 @default.
• W2022798421 cites W1989954041 @default.
• W2022798421 cites W1991139021 @default.
• W2022798421 cites W2005608041 @default.
• W2022798421 cites W2008565517 @default.
• W2022798421 cites W2015143272 @default.
• W2022798421 cites W2029564985 @default.
• W2022798421 cites W2037740282 @default.
• W2022798421 cites W2060822897 @default.
• W2022798421 cites W2079362249 @default.
• W2022798421 cites W2100969003 @default.
• W2022798421 cites W2119599673 @default.
• W2022798421 cites W2124149378 @default.
• W2022798421 cites W2130322773 @default.
• W2022798421 cites W2131816934 @default.
• W2022798421 cites W2138084857 @default.
• W2022798421 cites W2143341575 @default.
• W2022798421 cites W2144271355 @default.
• W2022798421 cites W2146871184 @default.
• W2022798421 cites W2149425615 @default.
• W2022798421 cites W2150415460 @default.
• W2022798421 cites W2155531311 @default.
• W2022798421 cites W2165108269 @default.
• W2022798421 cites W2567948266 @default.
• W2022798421 cites W4212863985 @default.
• W2022798421 cites W4245919820 @default.
• W2022798421 cites W4250589301 @default.
• W2022798421 cites W86348706 @default.
• W2022798421 doi "https://doi.org/10.1109/tasl.2013.2260744" @default.
• W2022798421 hasPublicationYear "2013" @default.
• W2022798421 type Work @default.
• W2022798421 sameAs 2022798421 @default.
• W2022798421 citedByCount "9" @default.
• W2022798421 countsByYear W20227984212013 @default.
• W2022798421 countsByYear W20227984212014 @default.
• W2022798421 countsByYear W20227984212016 @default.
• W2022798421 countsByYear W20227984212017 @default.
• W2022798421 countsByYear W20227984212018 @default.
• W2022798421 countsByYear W20227984212020 @default.
• W2022798421 crossrefType "journal-article" @default.
• W2022798421 hasAuthorship W2022798421A5015798259 @default.
• W2022798421 hasAuthorship W2022798421A5079103786 @default.
• W2022798421 hasConcept C104317684 @default.
• W2022798421 hasConcept C119857082 @default.
• W2022798421 hasConcept C120665830 @default.
• W2022798421 hasConcept C121332964 @default.
• W2022798421 hasConcept C134306372 @default.
• W2022798421 hasConcept C139807058 @default.
• W2022798421 hasConcept C154945302 @default.
• W2022798421 hasConcept C183763347 @default.
• W2022798421 hasConcept C185592680 @default.
• W2022798421 hasConcept C23224414 @default.
• W2022798421 hasConcept C2776214188 @default.
• W2022798421 hasConcept C28490314 @default.
• W2022798421 hasConcept C33923547 @default.
• W2022798421 hasConcept C41008148 @default.
• W2022798421 hasConcept C55493867 @default.
• W2022798421 hasConcept C63479239 @default.
• W2022798421 hasConceptScore W2022798421C104317684 @default.
• W2022798421 hasConceptScore W2022798421C119857082 @default.
• W2022798421 hasConceptScore W2022798421C120665830 @default.
• W2022798421 hasConceptScore W2022798421C121332964 @default.
• W2022798421 hasConceptScore W2022798421C134306372 @default.
• W2022798421 hasConceptScore W2022798421C139807058 @default.
• W2022798421 hasConceptScore W2022798421C154945302 @default.
• W2022798421 hasConceptScore W2022798421C183763347 @default.
• W2022798421 hasConceptScore W2022798421C185592680 @default.
• W2022798421 hasConceptScore W2022798421C23224414 @default.
• W2022798421 hasConceptScore W2022798421C2776214188 @default.
• W2022798421 hasConceptScore W2022798421C28490314 @default.
• W2022798421 hasConceptScore W2022798421C33923547 @default.
• W2022798421 hasConceptScore W2022798421C41008148 @default.
• W2022798421 hasConceptScore W2022798421C55493867 @default.
• W2022798421 hasConceptScore W2022798421C63479239 @default.
• W2022798421 hasIssue "8" @default.
• W2022798421 hasLocation W20227984211 @default.
• W2022798421 hasOpenAccess W2022798421 @default.
• W2022798421 hasPrimaryLocation W20227984211 @default.
• W2022798421 hasRelatedWork W1591475660 @default.
• W2022798421 hasRelatedWork W2001275470 @default.
• W2022798421 hasRelatedWork W2025614924 @default.
• W2022798421 hasRelatedWork W2097963413 @default.
• W2022798421 hasRelatedWork W2164162849 @default.
• W2022798421 hasRelatedWork W2294335174 @default.
• W2022798421 hasRelatedWork W2364370872 @default.
• W2022798421 hasRelatedWork W2735765216 @default.
• W2022798421 hasRelatedWork W2995886640 @default.
• W2022798421 hasRelatedWork W3145575561 @default.

• next