Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970568180> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2970568180 abstract "This paper presents a new speaker change detection system based on Long Short-Term Memory (LSTM) neural networks using acoustic data and linguistic content. Language modelling is combined with two different Joint Factor Analysis (JFA) acoustic approaches: i-vectors and speaker factors. Both of them are compared with a baseline algorithm that uses cosine distance to detect speaker turn changes. LSTM neural networks with both linguistic and acoustic features have been able to produce a robust speaker segmentation. The experimental results show that our proposal clearly outperforms the baseline system." @default.
- W2970568180 created "2019-09-05" @default.
- W2970568180 creator A5004224082 @default.
- W2970568180 creator A5025633053 @default.
- W2970568180 creator A5085739769 @default.
- W2970568180 date "2017-08-20" @default.
- W2970568180 modified "2023-10-12" @default.
- W2970568180 title "LSTM Neural Network-Based Speaker Segmentation Using Acoustic and Language Modelling" @default.
- W2970568180 cites W125260059 @default.
- W2970568180 cites W1556474518 @default.
- W2970568180 cites W1904365287 @default.
- W2970568180 cites W2075662881 @default.
- W2970568180 cites W2107638917 @default.
- W2970568180 cites W2125642021 @default.
- W2970568180 cites W2131571251 @default.
- W2970568180 cites W2150355110 @default.
- W2970568180 cites W2156255174 @default.
- W2970568180 cites W2402268235 @default.
- W2970568180 cites W2405802804 @default.
- W2970568180 cites W3146998960 @default.
- W2970568180 doi "https://doi.org/10.21437/interspeech.2017-407" @default.
- W2970568180 hasPublicationYear "2017" @default.
- W2970568180 type Work @default.
- W2970568180 sameAs 2970568180 @default.
- W2970568180 citedByCount "14" @default.
- W2970568180 countsByYear W29705681802017 @default.
- W2970568180 countsByYear W29705681802018 @default.
- W2970568180 countsByYear W29705681802019 @default.
- W2970568180 countsByYear W29705681802020 @default.
- W2970568180 countsByYear W29705681802021 @default.
- W2970568180 countsByYear W29705681802023 @default.
- W2970568180 crossrefType "proceedings-article" @default.
- W2970568180 hasAuthorship W2970568180A5004224082 @default.
- W2970568180 hasAuthorship W2970568180A5025633053 @default.
- W2970568180 hasAuthorship W2970568180A5085739769 @default.
- W2970568180 hasBestOaLocation W29705681802 @default.
- W2970568180 hasConcept C154945302 @default.
- W2970568180 hasConcept C204321447 @default.
- W2970568180 hasConcept C28490314 @default.
- W2970568180 hasConcept C41008148 @default.
- W2970568180 hasConcept C50644808 @default.
- W2970568180 hasConcept C89600930 @default.
- W2970568180 hasConceptScore W2970568180C154945302 @default.
- W2970568180 hasConceptScore W2970568180C204321447 @default.
- W2970568180 hasConceptScore W2970568180C28490314 @default.
- W2970568180 hasConceptScore W2970568180C41008148 @default.
- W2970568180 hasConceptScore W2970568180C50644808 @default.
- W2970568180 hasConceptScore W2970568180C89600930 @default.
- W2970568180 hasLocation W29705681801 @default.
- W2970568180 hasLocation W29705681802 @default.
- W2970568180 hasOpenAccess W2970568180 @default.
- W2970568180 hasPrimaryLocation W29705681801 @default.
- W2970568180 hasRelatedWork W2293457016 @default.
- W2970568180 hasRelatedWork W2351428524 @default.
- W2970568180 hasRelatedWork W2358941527 @default.
- W2970568180 hasRelatedWork W2368779261 @default.
- W2970568180 hasRelatedWork W2369308426 @default.
- W2970568180 hasRelatedWork W2386387936 @default.
- W2970568180 hasRelatedWork W2789919619 @default.
- W2970568180 hasRelatedWork W3169305685 @default.
- W2970568180 hasRelatedWork W1551406738 @default.
- W2970568180 hasRelatedWork W2610387714 @default.
- W2970568180 isParatext "false" @default.
- W2970568180 isRetracted "false" @default.
- W2970568180 magId "2970568180" @default.
- W2970568180 workType "article" @default.