On the Adequacy of Baseform Pronunciations and Pronunciation Variants thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

On the Adequacy of Baseform Pronunciations and Pronunciation Variants

Published on Feb 25, 20073915 Views

This paper presents an approach to automatically extract and evaluate the ``stability'' of pronunciation variants (i.e., adequacy of the model to accommodate this variability), based on multiple pronu

Related categories

Chapter list

Summary00:00
The 2004 ICSI-SRI-UW Meeting Recognition System00:16
Cast of Characters00:35
' 'Map' '01:45
The Meeting Task02:10
The Meeting Task03:59
Dev an Eval Data04:14
Meeting Training Data06:26
System Architecture07:32
Baseline System Development09:04
Old Baseline vs. New Baseline on Meeting Data10:12
Language Model Adaptation10:38
Acoustic Model Adaptation11:39
Noise Filtering13:01
Array Processing13:38
Segmentation15:12
Cross-talk Suppression16:37
RT-04 Dev vs. Eval18:22
Full CTS System Results19:09
Summary20:10
Summary20:26
Summary20:47
Conclusions21:22