Matches in SemOpenAlex for { <https://semopenalex.org/work/W2110123218> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2110123218 abstract "Approaches in Automatic Speech Recognition based on classic acoustic models seem not to exploit all the information lying in a speech signal; furthermore decoding procedures have real time constraints preventing the system to achieve optimal alignment between acoustic models and signal. In this paper, we present an approach to speech recognition in which Factorial Hidden Markov Models (FHMM) are used as syllabic acoustic models. An alignment algorithm is used for unit decoding. As applicative domain we choose numbers (range 0-999,999) uttered in Italian. Syllabic accuracy in our model is 84.81%, correctness on numbers is 77.74%. Aim of the experiment is to show that the performances of FHMMs lie in the ability to retrieve the presence of two different temporal dynamics in a speech segments: the former with a quasi-segmental timing, the latter presenting a quasi-syllabic trend. Moreover, we evaluate a unit decoding process based on a dynamic programming algorithm in order to exploit the acoustic models performances at best." @default.
- W2110123218 created "2016-06-24" @default.
- W2110123218 creator A5009188742 @default.
- W2110123218 creator A5023512165 @default.
- W2110123218 creator A5053960324 @default.
- W2110123218 date "2007-08-27" @default.
- W2110123218 modified "2023-09-26" @default.
- W2110123218 title "Speech recognition with factorial-HMM syllabic acoustic models" @default.
- W2110123218 cites W1528056001 @default.
- W2110123218 cites W1819207621 @default.
- W2110123218 cites W2053280194 @default.
- W2110123218 cites W2110075857 @default.
- W2110123218 cites W2140686411 @default.
- W2110123218 cites W2146608839 @default.
- W2110123218 cites W2154478440 @default.
- W2110123218 cites W2158286329 @default.
- W2110123218 cites W2160679028 @default.
- W2110123218 cites W2263610414 @default.
- W2110123218 cites W3216176320 @default.
- W2110123218 cites W88864901 @default.
- W2110123218 doi "https://doi.org/10.21437/interspeech.2007-320" @default.
- W2110123218 hasPublicationYear "2007" @default.
- W2110123218 type Work @default.
- W2110123218 sameAs 2110123218 @default.
- W2110123218 citedByCount "1" @default.
- W2110123218 countsByYear W21101232182022 @default.
- W2110123218 crossrefType "proceedings-article" @default.
- W2110123218 hasAuthorship W2110123218A5009188742 @default.
- W2110123218 hasAuthorship W2110123218A5023512165 @default.
- W2110123218 hasAuthorship W2110123218A5053960324 @default.
- W2110123218 hasConcept C134306372 @default.
- W2110123218 hasConcept C153180895 @default.
- W2110123218 hasConcept C154945302 @default.
- W2110123218 hasConcept C183763347 @default.
- W2110123218 hasConcept C194051139 @default.
- W2110123218 hasConcept C23224414 @default.
- W2110123218 hasConcept C28490314 @default.
- W2110123218 hasConcept C33923547 @default.
- W2110123218 hasConcept C41008148 @default.
- W2110123218 hasConceptScore W2110123218C134306372 @default.
- W2110123218 hasConceptScore W2110123218C153180895 @default.
- W2110123218 hasConceptScore W2110123218C154945302 @default.
- W2110123218 hasConceptScore W2110123218C183763347 @default.
- W2110123218 hasConceptScore W2110123218C194051139 @default.
- W2110123218 hasConceptScore W2110123218C23224414 @default.
- W2110123218 hasConceptScore W2110123218C28490314 @default.
- W2110123218 hasConceptScore W2110123218C33923547 @default.
- W2110123218 hasConceptScore W2110123218C41008148 @default.
- W2110123218 hasLocation W21101232181 @default.
- W2110123218 hasOpenAccess W2110123218 @default.
- W2110123218 hasPrimaryLocation W21101232181 @default.
- W2110123218 hasRelatedWork W1548481688 @default.
- W2110123218 hasRelatedWork W1995315771 @default.
- W2110123218 hasRelatedWork W2023185280 @default.
- W2110123218 hasRelatedWork W2110123218 @default.
- W2110123218 hasRelatedWork W2160799648 @default.
- W2110123218 hasRelatedWork W2374918184 @default.
- W2110123218 hasRelatedWork W2539985974 @default.
- W2110123218 hasRelatedWork W3128571556 @default.
- W2110123218 hasRelatedWork W4301681594 @default.
- W2110123218 hasRelatedWork W51696344 @default.
- W2110123218 isParatext "false" @default.
- W2110123218 isRetracted "false" @default.
- W2110123218 magId "2110123218" @default.
- W2110123218 workType "article" @default.