Wenda Chen Institute for Infocomm Research, A*STAR, Singapore and - - PowerPoint PPT Presentation

wenda chen
SMART_READER_LITE
LIVE PREVIEW

Wenda Chen Institute for Infocomm Research, A*STAR, Singapore and - - PowerPoint PPT Presentation

Wenda Chen Institute for Infocomm Research, A*STAR, Singapore and Nanyang Technological University, Singapore NTU project: Computer Assisted Language Learning System in Singapore English I 2 R project: Statistical analysis of the


slide-1
SLIDE 1

Wenda Chen

slide-2
SLIDE 2

 Institute for Infocomm Research, A*STAR,

Singapore and Nanyang Technological University, Singapore

 NTU project: Computer Assisted Language

Learning System in Singapore English

 I2R project: Statistical analysis of the Corpus

based pronunciation variation rule for pronunciation error detection and feedback in Singapore English

slide-3
SLIDE 3
slide-4
SLIDE 4
slide-5
SLIDE 5
slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9
slide-10
SLIDE 10

 Between training and testing data set

slide-11
SLIDE 11
slide-12
SLIDE 12

Buckeye corpus

slide-13
SLIDE 13
slide-14
SLIDE 14
slide-15
SLIDE 15
slide-16
SLIDE 16

 Dialect and mispronunciation detection  E{C=>F|b=K,d=M} estimation  F=g(C), estimate E{R|Test} based on E{R|Sg} and

E{R|Am}

 Statistical test, p value, binomial test, t test (degree

  • f freedom: no. of testing phones), multinomial

distribution of phone errors in SgE data, AmE data and test data

 MAP framework for phoneme error event detection

and finding the optimum threshold combination

 Vector subspace decomposition and representation of

  • riginal AmE into SgE phone set
slide-17
SLIDE 17
slide-18
SLIDE 18
slide-19
SLIDE 19
slide-20
SLIDE 20
slide-21
SLIDE 21
slide-22
SLIDE 22