Matches in SemOpenAlex for { <https://semopenalex.org/work/W2736984005> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2736984005 abstract "There are basically three areas which can be explored to improve an HMM based recognizer, namely, parameter extraction, training methods and vocabulary representation.The goal of parameter extraction is not only to find a compact and robust parametric representation of the speech signal, but also to find one which allows the HMMs to obtain the best possible recognition performance. Historically, improvements at this level have usually been obtained on a trial and error basis, using as much knowledge as possible about both the speech production and speech perception mechanisms. That is, the acoustic parameter extraction module has always been viewed as a separate module from the HMMs. This thesis will explore the concept of performing parameter extraction with a connectionist model, whose parameters can be learned from training data.Two HMM training techniques are used in this thesis, namely MLE and MMIE. Parameter initialization, of critical importance for both, will be investigated for discrete, semi-continuous and continuous HMMs. Training processes involving a combination of MLE and MMIE training are studied. Other issues such as codebook exponents and the use of pause and silence models will also be explored.Even if the vocabulary contains only 11 words, its representation is a very important issue. The effects of vocabulary representation with phoneme based, word based (with no sharing) and inter-word models will be experimentally evaluated. It will be shown how a word error rate of 0.23% and a string error rate of 0.68% can be achieved on the TIDIGITS corpus--a performance rivalling the best results ever reported by any group of researchers." @default.
- W2736984005 created "2017-07-31" @default.
- W2736984005 creator A5065576817 @default.
- W2736984005 creator A5081408760 @default.
- W2736984005 date "1994-01-01" @default.
- W2736984005 modified "2023-09-23" @default.
- W2736984005 title "Improved learning strategies for small vocabulary automatic speech recognition" @default.
- W2736984005 hasPublicationYear "1994" @default.
- W2736984005 type Work @default.
- W2736984005 sameAs 2736984005 @default.
- W2736984005 citedByCount "1" @default.
- W2736984005 countsByYear W27369840052012 @default.
- W2736984005 crossrefType "journal-article" @default.
- W2736984005 hasAuthorship W2736984005A5065576817 @default.
- W2736984005 hasAuthorship W2736984005A5081408760 @default.
- W2736984005 hasConcept C114466953 @default.
- W2736984005 hasConcept C138885662 @default.
- W2736984005 hasConcept C153180895 @default.
- W2736984005 hasConcept C154945302 @default.
- W2736984005 hasConcept C17744445 @default.
- W2736984005 hasConcept C199360897 @default.
- W2736984005 hasConcept C199539241 @default.
- W2736984005 hasConcept C204321447 @default.
- W2736984005 hasConcept C23224414 @default.
- W2736984005 hasConcept C2524010 @default.
- W2736984005 hasConcept C2776359362 @default.
- W2736984005 hasConcept C2777601683 @default.
- W2736984005 hasConcept C28490314 @default.
- W2736984005 hasConcept C33923547 @default.
- W2736984005 hasConcept C40969351 @default.
- W2736984005 hasConcept C41008148 @default.
- W2736984005 hasConcept C41895202 @default.
- W2736984005 hasConcept C90805587 @default.
- W2736984005 hasConcept C94625758 @default.
- W2736984005 hasConceptScore W2736984005C114466953 @default.
- W2736984005 hasConceptScore W2736984005C138885662 @default.
- W2736984005 hasConceptScore W2736984005C153180895 @default.
- W2736984005 hasConceptScore W2736984005C154945302 @default.
- W2736984005 hasConceptScore W2736984005C17744445 @default.
- W2736984005 hasConceptScore W2736984005C199360897 @default.
- W2736984005 hasConceptScore W2736984005C199539241 @default.
- W2736984005 hasConceptScore W2736984005C204321447 @default.
- W2736984005 hasConceptScore W2736984005C23224414 @default.
- W2736984005 hasConceptScore W2736984005C2524010 @default.
- W2736984005 hasConceptScore W2736984005C2776359362 @default.
- W2736984005 hasConceptScore W2736984005C2777601683 @default.
- W2736984005 hasConceptScore W2736984005C28490314 @default.
- W2736984005 hasConceptScore W2736984005C33923547 @default.
- W2736984005 hasConceptScore W2736984005C40969351 @default.
- W2736984005 hasConceptScore W2736984005C41008148 @default.
- W2736984005 hasConceptScore W2736984005C41895202 @default.
- W2736984005 hasConceptScore W2736984005C90805587 @default.
- W2736984005 hasConceptScore W2736984005C94625758 @default.
- W2736984005 hasLocation W27369840051 @default.
- W2736984005 hasOpenAccess W2736984005 @default.
- W2736984005 hasPrimaryLocation W27369840051 @default.
- W2736984005 hasRelatedWork W1494243555 @default.
- W2736984005 hasRelatedWork W1516698649 @default.
- W2736984005 hasRelatedWork W1529942162 @default.
- W2736984005 hasRelatedWork W1543325588 @default.
- W2736984005 hasRelatedWork W16789520 @default.
- W2736984005 hasRelatedWork W1845608487 @default.
- W2736984005 hasRelatedWork W1966324591 @default.
- W2736984005 hasRelatedWork W2013891821 @default.
- W2736984005 hasRelatedWork W2025688404 @default.
- W2736984005 hasRelatedWork W2074382434 @default.
- W2736984005 hasRelatedWork W2124923259 @default.
- W2736984005 hasRelatedWork W2413227220 @default.
- W2736984005 hasRelatedWork W2480328314 @default.
- W2736984005 hasRelatedWork W2510720084 @default.
- W2736984005 hasRelatedWork W2512449242 @default.
- W2736984005 hasRelatedWork W2541627266 @default.
- W2736984005 hasRelatedWork W2780038876 @default.
- W2736984005 hasRelatedWork W2890197052 @default.
- W2736984005 hasRelatedWork W92538581 @default.
- W2736984005 hasRelatedWork W2182518606 @default.
- W2736984005 isParatext "false" @default.
- W2736984005 isRetracted "false" @default.
- W2736984005 magId "2736984005" @default.
- W2736984005 workType "article" @default.