Matches in SemOpenAlex for { <https://semopenalex.org/work/W1966324591> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W1966324591 endingPage "S36" @default.
- W1966324591 startingPage "S36" @default.
- W1966324591 abstract "Recently, hidden Markov models (HMM) have been applied successfully to both isolated and connected word recognition. However, when the same formulation is adopted for recognition of more confusable vocabularies such as English alphabets, the recognition performance is often less satisfactory. The main reason is that a more accurate model is required. Such a model should be more robust against small training sample sizes and should also be properly initialized so that the finer features used to discriminate confusable word pairs can be extracted. In this paper, three specific robustness issues will be investigated: choice of observation densities, model initialization, and incorporation of duration information. In a step-by-step attempt to address those issues, it was found that the same HMM formulation can still be adopted if acoustic/phonetic knowledge about the vocabulary is taken into account in the model parameter estimation and recognition phases. Testing on a 39-word English alpha-digit vocabulary, in a speaker trained mode, indicates that the recognition performance can be significantly improved and the results are comparable to the template-based DTW recognizer if model parameters are properly initialized and durational information is adquately incorporated." @default.
- W1966324591 created "2016-06-24" @default.
- W1966324591 creator A5066868860 @default.
- W1966324591 date "1987-11-01" @default.
- W1966324591 modified "2023-09-24" @default.
- W1966324591 title "Some techniques for creating robust stochastic models for speech recognition" @default.
- W1966324591 doi "https://doi.org/10.1121/1.2024776" @default.
- W1966324591 hasPublicationYear "1987" @default.
- W1966324591 type Work @default.
- W1966324591 sameAs 1966324591 @default.
- W1966324591 citedByCount "2" @default.
- W1966324591 crossrefType "journal-article" @default.
- W1966324591 hasAuthorship W1966324591A5066868860 @default.
- W1966324591 hasBestOaLocation W19663245911 @default.
- W1966324591 hasConcept C104317684 @default.
- W1966324591 hasConcept C114466953 @default.
- W1966324591 hasConcept C138885662 @default.
- W1966324591 hasConcept C150856459 @default.
- W1966324591 hasConcept C153180895 @default.
- W1966324591 hasConcept C154945302 @default.
- W1966324591 hasConcept C17744445 @default.
- W1966324591 hasConcept C185592680 @default.
- W1966324591 hasConcept C199360897 @default.
- W1966324591 hasConcept C199539241 @default.
- W1966324591 hasConcept C23224414 @default.
- W1966324591 hasConcept C2524010 @default.
- W1966324591 hasConcept C2777601683 @default.
- W1966324591 hasConcept C28490314 @default.
- W1966324591 hasConcept C33923547 @default.
- W1966324591 hasConcept C41008148 @default.
- W1966324591 hasConcept C41895202 @default.
- W1966324591 hasConcept C554936623 @default.
- W1966324591 hasConcept C55493867 @default.
- W1966324591 hasConcept C63479239 @default.
- W1966324591 hasConcept C90805587 @default.
- W1966324591 hasConceptScore W1966324591C104317684 @default.
- W1966324591 hasConceptScore W1966324591C114466953 @default.
- W1966324591 hasConceptScore W1966324591C138885662 @default.
- W1966324591 hasConceptScore W1966324591C150856459 @default.
- W1966324591 hasConceptScore W1966324591C153180895 @default.
- W1966324591 hasConceptScore W1966324591C154945302 @default.
- W1966324591 hasConceptScore W1966324591C17744445 @default.
- W1966324591 hasConceptScore W1966324591C185592680 @default.
- W1966324591 hasConceptScore W1966324591C199360897 @default.
- W1966324591 hasConceptScore W1966324591C199539241 @default.
- W1966324591 hasConceptScore W1966324591C23224414 @default.
- W1966324591 hasConceptScore W1966324591C2524010 @default.
- W1966324591 hasConceptScore W1966324591C2777601683 @default.
- W1966324591 hasConceptScore W1966324591C28490314 @default.
- W1966324591 hasConceptScore W1966324591C33923547 @default.
- W1966324591 hasConceptScore W1966324591C41008148 @default.
- W1966324591 hasConceptScore W1966324591C41895202 @default.
- W1966324591 hasConceptScore W1966324591C554936623 @default.
- W1966324591 hasConceptScore W1966324591C55493867 @default.
- W1966324591 hasConceptScore W1966324591C63479239 @default.
- W1966324591 hasConceptScore W1966324591C90805587 @default.
- W1966324591 hasIssue "S1" @default.
- W1966324591 hasLocation W19663245911 @default.
- W1966324591 hasOpenAccess W1966324591 @default.
- W1966324591 hasPrimaryLocation W19663245911 @default.
- W1966324591 hasRelatedWork W1489815656 @default.
- W1966324591 hasRelatedWork W1980930823 @default.
- W1966324591 hasRelatedWork W2011731246 @default.
- W1966324591 hasRelatedWork W2038107365 @default.
- W1966324591 hasRelatedWork W2050755277 @default.
- W1966324591 hasRelatedWork W2053734335 @default.
- W1966324591 hasRelatedWork W2101346879 @default.
- W1966324591 hasRelatedWork W2154901823 @default.
- W1966324591 hasRelatedWork W2171506966 @default.
- W1966324591 hasRelatedWork W769890870 @default.
- W1966324591 hasVolume "82" @default.
- W1966324591 isParatext "false" @default.
- W1966324591 isRetracted "false" @default.
- W1966324591 magId "1966324591" @default.
- W1966324591 workType "article" @default.