Matches in SemOpenAlex for { <https://semopenalex.org/work/W2736005052> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2736005052 abstract "Good speaker recognition systems should identify the speaker irrespective of what is spoken, including non-speech sounds that are often produced during natural conversations. In this work, the inclusion of breath sounds in the training phase of the speaker recognition is analyzed using the popular Gaussian mixture model-universal background model (GMM-UBM) and deep neural network (DNN) based systems. It is shown that the DNN-based systems have a better learning capability to perform well even on unseen data compared to GMM-UBM-based systems. Specifically, enhancement in speaker recognition performance is obtained on unseen stressed speech data by training systems with both breath sounds and modal speech. Experimental results show that inclusion of breath sounds in training data reduces the equal error rate (EER) of the speaker recognition system on stressed speech by 40% to 50% in absolute terms. It is also shown that increasing the number of hidden layers help DNNs to improve the performance even on unseen data." @default.
- W2736005052 created "2017-07-21" @default.
- W2736005052 creator A5047383705 @default.
- W2736005052 creator A5069966738 @default.
- W2736005052 date "2017-05-01" @default.
- W2736005052 modified "2023-09-25" @default.
- W2736005052 title "Improved speaker recognition system for stressed speech using deep neural networks" @default.
- W2736005052 cites W1006777433 @default.
- W2736005052 cites W105311456 @default.
- W2736005052 cites W1494198834 @default.
- W2736005052 cites W1987783679 @default.
- W2736005052 cites W1998345532 @default.
- W2736005052 cites W2004497042 @default.
- W2736005052 cites W2009118216 @default.
- W2736005052 cites W2041823554 @default.
- W2736005052 cites W2046015436 @default.
- W2736005052 cites W2046056978 @default.
- W2736005052 cites W2067301010 @default.
- W2736005052 cites W2073017590 @default.
- W2736005052 cites W2118177361 @default.
- W2736005052 cites W2121812409 @default.
- W2736005052 cites W2129379984 @default.
- W2736005052 cites W2136879537 @default.
- W2736005052 cites W2150769028 @default.
- W2736005052 cites W2153903782 @default.
- W2736005052 cites W2165880886 @default.
- W2736005052 cites W2180844708 @default.
- W2736005052 cites W2344822617 @default.
- W2736005052 cites W2398313355 @default.
- W2736005052 cites W2401684398 @default.
- W2736005052 cites W2405950182 @default.
- W2736005052 cites W2407857848 @default.
- W2736005052 cites W2515254866 @default.
- W2736005052 cites W2962853205 @default.
- W2736005052 doi "https://doi.org/10.1109/ijcnn.2017.7965997" @default.
- W2736005052 hasPublicationYear "2017" @default.
- W2736005052 type Work @default.
- W2736005052 sameAs 2736005052 @default.
- W2736005052 citedByCount "11" @default.
- W2736005052 countsByYear W27360050522017 @default.
- W2736005052 countsByYear W27360050522018 @default.
- W2736005052 countsByYear W27360050522019 @default.
- W2736005052 countsByYear W27360050522021 @default.
- W2736005052 countsByYear W27360050522022 @default.
- W2736005052 crossrefType "proceedings-article" @default.
- W2736005052 hasAuthorship W2736005052A5047383705 @default.
- W2736005052 hasAuthorship W2736005052A5069966738 @default.
- W2736005052 hasConcept C133892786 @default.
- W2736005052 hasConcept C149838564 @default.
- W2736005052 hasConcept C153180895 @default.
- W2736005052 hasConcept C154945302 @default.
- W2736005052 hasConcept C28490314 @default.
- W2736005052 hasConcept C2984842247 @default.
- W2736005052 hasConcept C40969351 @default.
- W2736005052 hasConcept C41008148 @default.
- W2736005052 hasConcept C50644808 @default.
- W2736005052 hasConcept C51632099 @default.
- W2736005052 hasConcept C61224824 @default.
- W2736005052 hasConceptScore W2736005052C133892786 @default.
- W2736005052 hasConceptScore W2736005052C149838564 @default.
- W2736005052 hasConceptScore W2736005052C153180895 @default.
- W2736005052 hasConceptScore W2736005052C154945302 @default.
- W2736005052 hasConceptScore W2736005052C28490314 @default.
- W2736005052 hasConceptScore W2736005052C2984842247 @default.
- W2736005052 hasConceptScore W2736005052C40969351 @default.
- W2736005052 hasConceptScore W2736005052C41008148 @default.
- W2736005052 hasConceptScore W2736005052C50644808 @default.
- W2736005052 hasConceptScore W2736005052C51632099 @default.
- W2736005052 hasConceptScore W2736005052C61224824 @default.
- W2736005052 hasLocation W27360050521 @default.
- W2736005052 hasOpenAccess W2736005052 @default.
- W2736005052 hasPrimaryLocation W27360050521 @default.
- W2736005052 hasRelatedWork W1501076695 @default.
- W2736005052 hasRelatedWork W1565537953 @default.
- W2736005052 hasRelatedWork W1594739536 @default.
- W2736005052 hasRelatedWork W1607020250 @default.
- W2736005052 hasRelatedWork W1901264808 @default.
- W2736005052 hasRelatedWork W1943324956 @default.
- W2736005052 hasRelatedWork W2014836763 @default.
- W2736005052 hasRelatedWork W2025037086 @default.
- W2736005052 hasRelatedWork W2035938076 @default.
- W2736005052 hasRelatedWork W2078169166 @default.
- W2736005052 hasRelatedWork W2129996067 @default.
- W2736005052 hasRelatedWork W2184622236 @default.
- W2736005052 hasRelatedWork W2348426059 @default.
- W2736005052 hasRelatedWork W2398406965 @default.
- W2736005052 hasRelatedWork W2400136144 @default.
- W2736005052 hasRelatedWork W2964243145 @default.
- W2736005052 hasRelatedWork W3150075257 @default.
- W2736005052 hasRelatedWork W3185000007 @default.
- W2736005052 hasRelatedWork W80511928 @default.
- W2736005052 hasRelatedWork W2061992966 @default.
- W2736005052 isParatext "false" @default.
- W2736005052 isRetracted "false" @default.
- W2736005052 magId "2736005052" @default.
- W2736005052 workType "article" @default.