000002479 001__ 2479
000002479 005__ 20250430135253.0
000002479 0247_ $$2DOI$$a10.6083/M43F4MX9
000002479 037__ $$aETD
000002479 245__ $$aToward more effective acoustic model clustering by more efficient use of data in speech recognition
000002479 260__ $$bOregon Health and Sciences University
000002479 269__ $$a2002-06-01
000002479 336__ $$aDissertation
000002479 502__ $$bPh.D.
000002479 520__ $$aIn  current  large  vocabulary  continuous  speech  recognition  systems,  multivariate  Gaussian  mixture  distributions  and  context-dependent  phones,  typically  triphones,  are  used to achieve high  accuracy  acoustic models.  It is crucial to address the problem of  how  to estimate an extremely large number of  model parameters from a limited  amount of  training data.  The traditional approach uses  phonetic  decision tree based  context  clustering for  reducing  free  parameters. However,  this  approach  has several problems  that  might cause  system  performance  degradation. All  of these  problems  are  due  to the  fact  that  the traditional  approach  does  not  efficiently  use  the limited  training data and  therefore  fails to obtain effective acoustic models.
000002479 542__ $$fIn copyright - single owner
000002479 650__ $$aPhonetics$$024006
000002479 650__ $$aSpeech Recognition Software$$036177
000002479 691__ $$aOGI School of Science and Engineering$$041365
000002479 692__ $$aOGI Department of Computer Science and Engineering$$041405
000002479 7001_ $$aLiu, Chaojun$$uOregon Health and Science University$$041354
000002479 7201_ $$aYan, Yonghong$$uOregon Health and Science University$$041354$$7Personal$$eAdvisor
000002479 8564_ $$9785d980c-09f3-4192-9242-c3cd8ba72054$$s3970292$$uhttps://digitalcollections.ohsu.edu/record/2479/files/3220_etd.pdf$$ePublic$$24b5ac5b066b1be15ef522d94e3f66457$$31
000002479 905__ $$a/rest/prod/v4/05/s9/62/v405s962n
000002479 909CO $$ooai:digitalcollections.ohsu.edu:2479$$pstudent-work
000002479 980__ $$aTheses and Dissertations