Matches in SemOpenAlex for { <https://semopenalex.org/work/W80876278> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W80876278 abstract "For noise-robust automatic speech recognition (ASR), we propose a novel voice activity detection (VAD) method based on a combination of multiple features. The scheme uses a weighted combination of four conventionalVAD features: amplitude level, zero crossing rate, spectral information, and Gaussian mixture model (GMM) likelihood. The weights for combination are adaptively updated using minimum classification error (MCE) training. In this paper, we first investigate the effect of adaptation of the combination weights and GMM parameters, and demonstrate that the weights can be effectively adapted with a single utterance. Then, we present application of the method to ASR. It is confirmed that the proposed method significantly outperforms conventional methods in various noise conditions. Index Terms: speech recognition, voice activity detection, MCE training, noise adaptation" @default.
- W80876278 created "2016-06-24" @default.
- W80876278 creator A5027907338 @default.
- W80876278 creator A5038044080 @default.
- W80876278 date "2006-09-17" @default.
- W80876278 modified "2023-10-04" @default.
- W80876278 title "Evaluation of voice activity detection by combining multiple features with weight adaptation" @default.
- W80876278 cites W1536730100 @default.
- W80876278 cites W16670509 @default.
- W80876278 cites W2129120544 @default.
- W80876278 cites W2162969672 @default.
- W80876278 cites W2166607750 @default.
- W80876278 cites W86289693 @default.
- W80876278 cites W2507954479 @default.
- W80876278 doi "https://doi.org/10.21437/interspeech.2006-539" @default.
- W80876278 hasPublicationYear "2006" @default.
- W80876278 type Work @default.
- W80876278 sameAs 80876278 @default.
- W80876278 citedByCount "5" @default.
- W80876278 countsByYear W808762782014 @default.
- W80876278 countsByYear W808762782020 @default.
- W80876278 crossrefType "proceedings-article" @default.
- W80876278 hasAuthorship W80876278A5027907338 @default.
- W80876278 hasAuthorship W80876278A5038044080 @default.
- W80876278 hasConcept C139807058 @default.
- W80876278 hasConcept C154945302 @default.
- W80876278 hasConcept C15744967 @default.
- W80876278 hasConcept C169760540 @default.
- W80876278 hasConcept C204201278 @default.
- W80876278 hasConcept C28490314 @default.
- W80876278 hasConcept C41008148 @default.
- W80876278 hasConcept C61328038 @default.
- W80876278 hasConceptScore W80876278C139807058 @default.
- W80876278 hasConceptScore W80876278C154945302 @default.
- W80876278 hasConceptScore W80876278C15744967 @default.
- W80876278 hasConceptScore W80876278C169760540 @default.
- W80876278 hasConceptScore W80876278C204201278 @default.
- W80876278 hasConceptScore W80876278C28490314 @default.
- W80876278 hasConceptScore W80876278C41008148 @default.
- W80876278 hasConceptScore W80876278C61328038 @default.
- W80876278 hasLocation W808762781 @default.
- W80876278 hasOpenAccess W80876278 @default.
- W80876278 hasPrimaryLocation W808762781 @default.
- W80876278 hasRelatedWork W1522515376 @default.
- W80876278 hasRelatedWork W1571518467 @default.
- W80876278 hasRelatedWork W189527659 @default.
- W80876278 hasRelatedWork W2076610045 @default.
- W80876278 hasRelatedWork W2102118225 @default.
- W80876278 hasRelatedWork W2135470563 @default.
- W80876278 hasRelatedWork W2368779261 @default.
- W80876278 hasRelatedWork W2778699561 @default.
- W80876278 hasRelatedWork W2893763841 @default.
- W80876278 hasRelatedWork W87991986 @default.
- W80876278 isParatext "false" @default.
- W80876278 isRetracted "false" @default.
- W80876278 magId "80876278" @default.
- W80876278 workType "article" @default.