Matches in SemOpenAlex for { <https://semopenalex.org/work/W2242808236> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2242808236 abstract "Spoken Term Detection (STD) is the task of searching a given spoken query word in large speech database. Applications of STD include speech data indexing, voice dialling, telephone monitoring and data mining. Performance of STD depends mainly on representation of speech signal and matching of represented signal. This work investigates methods for robust representation of speech signal, which is invariant to speaker variability, in the context of STD task. Here the representation is in the form of templates, a sequence of feature vectors. Typical representation in speech community Mel-Frequency CepstralCoe cients (MFCC) carry both speech-specific and speaker-specific information, so the need for better representation. Searching is done by matching sequence of feature vectors of query and reference utterances by using Subsequence Dynamic Time Warping (DTW). The performance of the proposed representation is evaluated on Telugu broadcast news data. In the absence of labelled data i.e., in unsupervised setting, we propose to capture joint density of acoustic space spanned by MFCCs using Gaussian Mixture Models (GMM) and Gaussian-Bernoulli Restricted Boltzmann Machines (GBRBM). Posterior features extracted from trained models are used to search the query word. It is noticed that 8% and 12% improvement in STD performance compared to MFCC by using GMM and GBRBM posterior features respectively. As transcribed data is not required, this approach is optimal solution to low-resource languages. But due to it’s intermediate performance, this method cannot be immediate solution to high resource languages" @default.
- W2242808236 created "2016-06-24" @default.
- W2242808236 creator A5073024001 @default.
- W2242808236 date "2016-12-07" @default.
- W2242808236 modified "2023-10-17" @default.
- W2242808236 title "Representation Learning for Spoken Term Detection" @default.
- W2242808236 cites W114193738 @default.
- W2242808236 cites W1578200545 @default.
- W2242808236 cites W1594921063 @default.
- W2242808236 cites W1606311031 @default.
- W2242808236 cites W1607988020 @default.
- W2242808236 cites W170732776 @default.
- W2242808236 cites W1885329076 @default.
- W2242808236 cites W1963706776 @default.
- W2242808236 cites W202593991 @default.
- W2242808236 cites W2100495367 @default.
- W2242808236 cites W2103371184 @default.
- W2242808236 cites W2107091848 @default.
- W2242808236 cites W2110589736 @default.
- W2242808236 cites W2110758086 @default.
- W2242808236 cites W2114347655 @default.
- W2242808236 cites W2114478143 @default.
- W2242808236 cites W2114510609 @default.
- W2242808236 cites W2116620547 @default.
- W2242808236 cites W2122797512 @default.
- W2242808236 cites W2124776405 @default.
- W2242808236 cites W2125838338 @default.
- W2242808236 cites W2126203737 @default.
- W2242808236 cites W2148986421 @default.
- W2242808236 cites W2166343746 @default.
- W2242808236 cites W2166778951 @default.
- W2242808236 cites W2168080440 @default.
- W2242808236 cites W2171019095 @default.
- W2242808236 cites W2188600765 @default.
- W2242808236 cites W223359644 @default.
- W2242808236 cites W2293210169 @default.
- W2242808236 cites W2405666970 @default.
- W2242808236 cites W2442329935 @default.
- W2242808236 cites W2594610113 @default.
- W2242808236 cites W269707310 @default.
- W2242808236 cites W2799046698 @default.
- W2242808236 cites W66838807 @default.
- W2242808236 cites W965758856 @default.
- W2242808236 doi "https://doi.org/10.1142/9789813144552_0019" @default.
- W2242808236 hasPublicationYear "2016" @default.
- W2242808236 type Work @default.
- W2242808236 sameAs 2242808236 @default.
- W2242808236 citedByCount "0" @default.
- W2242808236 crossrefType "book-chapter" @default.
- W2242808236 hasAuthorship W2242808236A5073024001 @default.
- W2242808236 hasConcept C121332964 @default.
- W2242808236 hasConcept C1276947 @default.
- W2242808236 hasConcept C154945302 @default.
- W2242808236 hasConcept C17744445 @default.
- W2242808236 hasConcept C199539241 @default.
- W2242808236 hasConcept C204321447 @default.
- W2242808236 hasConcept C2776359362 @default.
- W2242808236 hasConcept C41008148 @default.
- W2242808236 hasConcept C61797465 @default.
- W2242808236 hasConcept C94625758 @default.
- W2242808236 hasConceptScore W2242808236C121332964 @default.
- W2242808236 hasConceptScore W2242808236C1276947 @default.
- W2242808236 hasConceptScore W2242808236C154945302 @default.
- W2242808236 hasConceptScore W2242808236C17744445 @default.
- W2242808236 hasConceptScore W2242808236C199539241 @default.
- W2242808236 hasConceptScore W2242808236C204321447 @default.
- W2242808236 hasConceptScore W2242808236C2776359362 @default.
- W2242808236 hasConceptScore W2242808236C41008148 @default.
- W2242808236 hasConceptScore W2242808236C61797465 @default.
- W2242808236 hasConceptScore W2242808236C94625758 @default.
- W2242808236 hasLocation W22428082361 @default.
- W2242808236 hasOpenAccess W2242808236 @default.
- W2242808236 hasPrimaryLocation W22428082361 @default.
- W2242808236 hasRelatedWork W1512718085 @default.
- W2242808236 hasRelatedWork W1569841287 @default.
- W2242808236 hasRelatedWork W2167662847 @default.
- W2242808236 hasRelatedWork W2293457016 @default.
- W2242808236 hasRelatedWork W2351428524 @default.
- W2242808236 hasRelatedWork W2359001871 @default.
- W2242808236 hasRelatedWork W2369308426 @default.
- W2242808236 hasRelatedWork W2789919619 @default.
- W2242808236 hasRelatedWork W1551406738 @default.
- W2242808236 hasRelatedWork W2610387714 @default.
- W2242808236 isParatext "false" @default.
- W2242808236 isRetracted "false" @default.
- W2242808236 magId "2242808236" @default.
- W2242808236 workType "book-chapter" @default.