Table of Contents
Pronunciation Modeling of Mandarin Casual Speech
Project Objectives
CASS Corpus Review
CASS Corpus Review
Chinese Segmental Labeling Convention SAMPA-C
Generalized Initial/Final (GIF)
Variability in the CASS Corpus
PPT Slide
Overview Map (GIF/IF Modeling on CASS)
Overview Map (Decision Tree Approach)
Flexible Alignment Tool
Flexible Alignment Tools
PPT Slide
PPT Slide
PPT Slide
PPT Slide
Extensibility of the Aligner
GIF/IF Pronunciation Modeling
GIF/IF Sparse Data
Probabilistic GIF
State Level Gaussian Sharing
State Level Gaussian Sharing
State Level Gaussian Sharing
Deleted Interpolation of IF/GIF Models
Deleted Interpolation of IF/GIF Models
PPT Slide
Discussion of Experimental Results
GIF/IF Pronunciation Modeling
Probabilistic Pronunciation Models
Acoustic Modeling of IF/GIF with Sparse Data: P(a|k,
s)
Using Context Equivalence Classes for P(s|k)
Experimental Results
Comparison Among Equal-Probability, DOP, and CDW
Discussion of Experimental Results
On going work: Pronunciation Modeling with Sparse
GIF Data
Predictive Features for Pronunciation Modeling
Sound Changes Annotated in CASS
Predicting Voicing Directly
High Correlation with Linguistic Transcription
of Voicing Feature
Using Voicing
Training Pronunciation Models on CASS
Training Pronunciation Models on CASS
Incorporation of Acoustic Features into Pronunciation
Models
Deriving Regular Phone Change Patterns From The
CASS Corpus
Example `Artificial' Phone Change
Apply CASS Pronunciation Models to Broadcast News
Data
Mandarin Broadcast News Evaluation
Ongoing Work: Inching Towards GIFs
Alternatives to Explicit GIF Models
Example (real) Triphone Clustering Trees Using
Acoustic Side Information
End of Presentation
Important Points
Important Points
Important Points
Important Points |