Matches in SemOpenAlex for { <https://semopenalex.org/work/W2407751501> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2407751501 abstract "Voice Activity Detection in movies is a non-trivial and challenging task. The different emotional states of the speakers, as well as the variety of soundscapes and noises contribute to the complexity of the task. In this paper, we propose a set of lightweight features that are specifically designed to perform under such conditions, while at the same time preventing confusions of singing voice with speech. For evaluation, we use four fulllength movies, previously unseen to the system and painstakingly annotated. We compare our detector to a state-of-the-art reference system. The new approach performs better, yielding just about half the Equal Error Rate (EER). Furthermore, since the ground truth annotation task is extremely tedious, and to help with advancing in this topic, we release the annotations of all four movies to the research community. Index Terms: Voice Activity Detection, Speech Detection" @default.
- W2407751501 created "2016-06-24" @default.
- W2407751501 creator A5003768123 @default.
- W2407751501 creator A5053582419 @default.
- W2407751501 creator A5064439379 @default.
- W2407751501 date "2015-09-06" @default.
- W2407751501 modified "2023-09-26" @default.
- W2407751501 title "Improving voice activity detection in movies" @default.
- W2407751501 cites W1501620 @default.
- W2407751501 cites W1999454387 @default.
- W2407751501 cites W2007664495 @default.
- W2407751501 cites W2085662862 @default.
- W2407751501 cites W2098265087 @default.
- W2407751501 cites W2109788549 @default.
- W2407751501 cites W2125324924 @default.
- W2407751501 cites W2125514156 @default.
- W2407751501 cites W2129120544 @default.
- W2407751501 cites W2133990480 @default.
- W2407751501 cites W2136105097 @default.
- W2407751501 cites W2136155127 @default.
- W2407751501 cites W2143582430 @default.
- W2407751501 cites W2144499799 @default.
- W2407751501 cites W2170348535 @default.
- W2407751501 cites W2619993508 @default.
- W2407751501 cites W304112886 @default.
- W2407751501 cites W3127686677 @default.
- W2407751501 cites W3140355440 @default.
- W2407751501 doi "https://doi.org/10.21437/interspeech.2015-455" @default.
- W2407751501 hasPublicationYear "2015" @default.
- W2407751501 type Work @default.
- W2407751501 sameAs 2407751501 @default.
- W2407751501 citedByCount "4" @default.
- W2407751501 countsByYear W24077515012017 @default.
- W2407751501 countsByYear W24077515012018 @default.
- W2407751501 countsByYear W24077515012020 @default.
- W2407751501 crossrefType "proceedings-article" @default.
- W2407751501 hasAuthorship W2407751501A5003768123 @default.
- W2407751501 hasAuthorship W2407751501A5053582419 @default.
- W2407751501 hasAuthorship W2407751501A5064439379 @default.
- W2407751501 hasConcept C127413603 @default.
- W2407751501 hasConcept C136197465 @default.
- W2407751501 hasConcept C146849305 @default.
- W2407751501 hasConcept C154945302 @default.
- W2407751501 hasConcept C162324750 @default.
- W2407751501 hasConcept C177264268 @default.
- W2407751501 hasConcept C187736073 @default.
- W2407751501 hasConcept C199360897 @default.
- W2407751501 hasConcept C201995342 @default.
- W2407751501 hasConcept C204201278 @default.
- W2407751501 hasConcept C204321447 @default.
- W2407751501 hasConcept C2776321320 @default.
- W2407751501 hasConcept C2780451532 @default.
- W2407751501 hasConcept C28490314 @default.
- W2407751501 hasConcept C41008148 @default.
- W2407751501 hasConcept C44819458 @default.
- W2407751501 hasConcept C61328038 @default.
- W2407751501 hasConceptScore W2407751501C127413603 @default.
- W2407751501 hasConceptScore W2407751501C136197465 @default.
- W2407751501 hasConceptScore W2407751501C146849305 @default.
- W2407751501 hasConceptScore W2407751501C154945302 @default.
- W2407751501 hasConceptScore W2407751501C162324750 @default.
- W2407751501 hasConceptScore W2407751501C177264268 @default.
- W2407751501 hasConceptScore W2407751501C187736073 @default.
- W2407751501 hasConceptScore W2407751501C199360897 @default.
- W2407751501 hasConceptScore W2407751501C201995342 @default.
- W2407751501 hasConceptScore W2407751501C204201278 @default.
- W2407751501 hasConceptScore W2407751501C204321447 @default.
- W2407751501 hasConceptScore W2407751501C2776321320 @default.
- W2407751501 hasConceptScore W2407751501C2780451532 @default.
- W2407751501 hasConceptScore W2407751501C28490314 @default.
- W2407751501 hasConceptScore W2407751501C41008148 @default.
- W2407751501 hasConceptScore W2407751501C44819458 @default.
- W2407751501 hasConceptScore W2407751501C61328038 @default.
- W2407751501 hasLocation W24077515011 @default.
- W2407751501 hasOpenAccess W2407751501 @default.
- W2407751501 hasPrimaryLocation W24077515011 @default.
- W2407751501 hasRelatedWork W2157241021 @default.
- W2407751501 hasRelatedWork W2340995799 @default.
- W2407751501 hasRelatedWork W2407151108 @default.
- W2407751501 hasRelatedWork W2809767522 @default.
- W2407751501 hasRelatedWork W2963887950 @default.
- W2407751501 hasRelatedWork W3011197176 @default.
- W2407751501 hasRelatedWork W3017847795 @default.
- W2407751501 hasRelatedWork W3024559545 @default.
- W2407751501 hasRelatedWork W3025871391 @default.
- W2407751501 hasRelatedWork W3034514362 @default.
- W2407751501 hasRelatedWork W3082779874 @default.
- W2407751501 hasRelatedWork W3095972178 @default.
- W2407751501 hasRelatedWork W3113320605 @default.
- W2407751501 hasRelatedWork W3120554508 @default.
- W2407751501 hasRelatedWork W3143035657 @default.
- W2407751501 hasRelatedWork W3163320179 @default.
- W2407751501 hasRelatedWork W3174674681 @default.
- W2407751501 hasRelatedWork W3209871323 @default.
- W2407751501 hasRelatedWork W3213227271 @default.
- W2407751501 hasRelatedWork W3213458023 @default.
- W2407751501 isParatext "false" @default.
- W2407751501 isRetracted "false" @default.
- W2407751501 magId "2407751501" @default.
- W2407751501 workType "article" @default.