Matches in SemOpenAlex for { <https://semopenalex.org/work/W146976060> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W146976060 abstract "This paper proposes to use non-negative matrix factorization based speech enhancement in robust automatic recognition of mixtures of speech and music. We represent magnitude spectra of noisy speech signals as the non-negative weighted linear combination of speech and noise spectral basis vectors, that are obtained from training corpora of speech and music. We use overcomplete dictionaries consisting of random exemplars of the training data. The method is tested on theWall Street Journal large vocabulary speech corpus which is artificially corrupted with polyphonic music from the RWC music database. Various music styles and speech-tomusic ratios are evaluated. The proposed methods are shown to produce a consistent, significant improvement on the recognition performance in the comparison with the baseline method. Audio demonstrations of the enhanced signals are available at http://www.cs.tut.fi/ tuomasv." @default.
- W146976060 created "2016-06-24" @default.
- W146976060 creator A5011157550 @default.
- W146976060 creator A5016771874 @default.
- W146976060 creator A5049691461 @default.
- W146976060 creator A5083515346 @default.
- W146976060 date "2010-09-26" @default.
- W146976060 modified "2023-10-14" @default.
- W146976060 title "Non-negative matrix factorization based compensation of music for automatic speech recognition" @default.
- W146976060 cites W1547060653 @default.
- W146976060 cites W16345605 @default.
- W146976060 cites W1800365115 @default.
- W146976060 cites W2000911789 @default.
- W146976060 cites W2079362249 @default.
- W146976060 cites W2106958364 @default.
- W146976060 cites W2115086266 @default.
- W146976060 cites W2121973264 @default.
- W146976060 cites W2126597753 @default.
- W146976060 cites W2128653836 @default.
- W146976060 cites W2150415460 @default.
- W146976060 cites W2150863656 @default.
- W146976060 cites W2151125621 @default.
- W146976060 doi "https://doi.org/10.21437/interspeech.2010-268" @default.
- W146976060 hasPublicationYear "2010" @default.
- W146976060 type Work @default.
- W146976060 sameAs 146976060 @default.
- W146976060 citedByCount "78" @default.
- W146976060 countsByYear W1469760602012 @default.
- W146976060 countsByYear W1469760602013 @default.
- W146976060 countsByYear W1469760602014 @default.
- W146976060 countsByYear W1469760602015 @default.
- W146976060 countsByYear W1469760602016 @default.
- W146976060 countsByYear W1469760602017 @default.
- W146976060 countsByYear W1469760602018 @default.
- W146976060 countsByYear W1469760602019 @default.
- W146976060 countsByYear W1469760602020 @default.
- W146976060 countsByYear W1469760602021 @default.
- W146976060 countsByYear W1469760602023 @default.
- W146976060 crossrefType "proceedings-article" @default.
- W146976060 hasAuthorship W146976060A5011157550 @default.
- W146976060 hasAuthorship W146976060A5016771874 @default.
- W146976060 hasAuthorship W146976060A5049691461 @default.
- W146976060 hasAuthorship W146976060A5083515346 @default.
- W146976060 hasConcept C11171543 @default.
- W146976060 hasConcept C121332964 @default.
- W146976060 hasConcept C152671427 @default.
- W146976060 hasConcept C153180895 @default.
- W146976060 hasConcept C154945302 @default.
- W146976060 hasConcept C15744967 @default.
- W146976060 hasConcept C158693339 @default.
- W146976060 hasConcept C2780023022 @default.
- W146976060 hasConcept C28490314 @default.
- W146976060 hasConcept C41008148 @default.
- W146976060 hasConcept C42355184 @default.
- W146976060 hasConcept C62520636 @default.
- W146976060 hasConceptScore W146976060C11171543 @default.
- W146976060 hasConceptScore W146976060C121332964 @default.
- W146976060 hasConceptScore W146976060C152671427 @default.
- W146976060 hasConceptScore W146976060C153180895 @default.
- W146976060 hasConceptScore W146976060C154945302 @default.
- W146976060 hasConceptScore W146976060C15744967 @default.
- W146976060 hasConceptScore W146976060C158693339 @default.
- W146976060 hasConceptScore W146976060C2780023022 @default.
- W146976060 hasConceptScore W146976060C28490314 @default.
- W146976060 hasConceptScore W146976060C41008148 @default.
- W146976060 hasConceptScore W146976060C42355184 @default.
- W146976060 hasConceptScore W146976060C62520636 @default.
- W146976060 hasLocation W1469760601 @default.
- W146976060 hasOpenAccess W146976060 @default.
- W146976060 hasPrimaryLocation W1469760601 @default.
- W146976060 hasRelatedWork W1568451138 @default.
- W146976060 hasRelatedWork W2037504162 @default.
- W146976060 hasRelatedWork W2045265907 @default.
- W146976060 hasRelatedWork W2075222291 @default.
- W146976060 hasRelatedWork W2127243424 @default.
- W146976060 hasRelatedWork W2146544734 @default.
- W146976060 hasRelatedWork W2156699640 @default.
- W146976060 hasRelatedWork W2539013788 @default.
- W146976060 hasRelatedWork W2792706544 @default.
- W146976060 hasRelatedWork W4287022770 @default.
- W146976060 isParatext "false" @default.
- W146976060 isRetracted "false" @default.
- W146976060 magId "146976060" @default.
- W146976060 workType "article" @default.