Matches in SemOpenAlex for { <https://semopenalex.org/work/W2889492015> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2889492015 abstract "The recent speaker embeddings framework has been shown to provide excellent performance on the task of text-independent speaker recognition. The framework is based on a deep neural network (DNN) trained to directly discriminate between speakers from traditional acoustic features such as Mel frequency cepstral coefficients. Prior studies on speaker recognition have found that phonetic information is valuable in the task of speaker identification, with systems being based on either bottleneck features (BFs) or tied-triphone state posteriors from a DNN trained for the task of speech recognition. In this paper, we analyze the role of phonetic BFs for DNN embeddings and explore methods to enhance the BFs further. Experimental results show that exploiting phonetic information encoded in BFs is very valuable for DNN speaker embeddings. Enriching the BFs using a cascaded DNN multi-task architecture is also shown to provide further improvements to the speaker embed- ding system." @default.
- W2889492015 created "2018-09-07" @default.
- W2889492015 creator A5034095159 @default.
- W2889492015 creator A5039529498 @default.
- W2889492015 creator A5055128383 @default.
- W2889492015 creator A5060382325 @default.
- W2889492015 creator A5068563214 @default.
- W2889492015 date "2018-09-02" @default.
- W2889492015 modified "2023-09-25" @default.
- W2889492015 title "Employing Phonetic Information in DNN Speaker Embeddings to Improve Speaker Recognition Performance" @default.
- W2889492015 cites W151003953 @default.
- W2889492015 cites W1524333225 @default.
- W2889492015 cites W1528954144 @default.
- W2889492015 cites W2046056978 @default.
- W2889492015 cites W2078169166 @default.
- W2889492015 cites W2094035326 @default.
- W2889492015 cites W2150769028 @default.
- W2889492015 cites W2185814970 @default.
- W2889492015 cites W2194775991 @default.
- W2889492015 cites W2515282169 @default.
- W2889492015 cites W2587150483 @default.
- W2889492015 cites W2696967604 @default.
- W2889492015 cites W2748488820 @default.
- W2889492015 cites W2807305309 @default.
- W2889492015 cites W3099206234 @default.
- W2889492015 doi "https://doi.org/10.21437/interspeech.2018-1804" @default.
- W2889492015 hasPublicationYear "2018" @default.
- W2889492015 type Work @default.
- W2889492015 sameAs 2889492015 @default.
- W2889492015 citedByCount "6" @default.
- W2889492015 countsByYear W28894920152019 @default.
- W2889492015 countsByYear W28894920152020 @default.
- W2889492015 countsByYear W28894920152021 @default.
- W2889492015 countsByYear W28894920152022 @default.
- W2889492015 crossrefType "proceedings-article" @default.
- W2889492015 hasAuthorship W2889492015A5034095159 @default.
- W2889492015 hasAuthorship W2889492015A5039529498 @default.
- W2889492015 hasAuthorship W2889492015A5055128383 @default.
- W2889492015 hasAuthorship W2889492015A5060382325 @default.
- W2889492015 hasAuthorship W2889492015A5068563214 @default.
- W2889492015 hasBestOaLocation W28894920152 @default.
- W2889492015 hasConcept C133892786 @default.
- W2889492015 hasConcept C149635348 @default.
- W2889492015 hasConcept C149838564 @default.
- W2889492015 hasConcept C151989614 @default.
- W2889492015 hasConcept C153180895 @default.
- W2889492015 hasConcept C154945302 @default.
- W2889492015 hasConcept C162324750 @default.
- W2889492015 hasConcept C187736073 @default.
- W2889492015 hasConcept C23224414 @default.
- W2889492015 hasConcept C2780451532 @default.
- W2889492015 hasConcept C2780513914 @default.
- W2889492015 hasConcept C28490314 @default.
- W2889492015 hasConcept C41008148 @default.
- W2889492015 hasConcept C50644808 @default.
- W2889492015 hasConcept C52622490 @default.
- W2889492015 hasConcept C88485024 @default.
- W2889492015 hasConceptScore W2889492015C133892786 @default.
- W2889492015 hasConceptScore W2889492015C149635348 @default.
- W2889492015 hasConceptScore W2889492015C149838564 @default.
- W2889492015 hasConceptScore W2889492015C151989614 @default.
- W2889492015 hasConceptScore W2889492015C153180895 @default.
- W2889492015 hasConceptScore W2889492015C154945302 @default.
- W2889492015 hasConceptScore W2889492015C162324750 @default.
- W2889492015 hasConceptScore W2889492015C187736073 @default.
- W2889492015 hasConceptScore W2889492015C23224414 @default.
- W2889492015 hasConceptScore W2889492015C2780451532 @default.
- W2889492015 hasConceptScore W2889492015C2780513914 @default.
- W2889492015 hasConceptScore W2889492015C28490314 @default.
- W2889492015 hasConceptScore W2889492015C41008148 @default.
- W2889492015 hasConceptScore W2889492015C50644808 @default.
- W2889492015 hasConceptScore W2889492015C52622490 @default.
- W2889492015 hasConceptScore W2889492015C88485024 @default.
- W2889492015 hasLocation W28894920151 @default.
- W2889492015 hasLocation W28894920152 @default.
- W2889492015 hasOpenAccess W2889492015 @default.
- W2889492015 hasPrimaryLocation W28894920151 @default.
- W2889492015 hasRelatedWork W2135998079 @default.
- W2889492015 hasRelatedWork W2151396723 @default.
- W2889492015 hasRelatedWork W2362672010 @default.
- W2889492015 hasRelatedWork W2383152411 @default.
- W2889492015 hasRelatedWork W2399347239 @default.
- W2889492015 hasRelatedWork W2889492015 @default.
- W2889492015 hasRelatedWork W2941574460 @default.
- W2889492015 hasRelatedWork W3186851455 @default.
- W2889492015 hasRelatedWork W40124310 @default.
- W2889492015 hasRelatedWork W2416972381 @default.
- W2889492015 isParatext "false" @default.
- W2889492015 isRetracted "false" @default.
- W2889492015 magId "2889492015" @default.
- W2889492015 workType "article" @default.