en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Advances in Phonetics-based Sub-Unit Modeling for Transcription, Alignment and Sign Language Recognition
Published on Aug 24, 20113959 Views
We explore novel directions for incorporating phonetic transcriptions into sub-unit based statistical models for sign language recognition. First, we employ a new symbolic processing approach for conv
Related categories
Chapter list
Advances in Phonetics-based Sub-Unit Modelingfor Transcription, Alignment and Sign Language Recognition.00:00
Overview00:20
Gestures versus Signs01:28
SL Recognition vs Gesture Recognition02:45
Subunit Modeling03:42
Goals of this Presentation05:06
Sign Language Data05:39
Interlaced data and pre-processing06:59
Tracking Video, GSL Lemmas Corpus07:50
Data-Driven Subunit Modeling08:44
Dynamic-Static SU Recognition10:43
Dynamic-Static SU Extraction - 111:16
Dynamic-Static SU Extraction - 213:42
Phonetic Modeling14:38
Phonetics14:55
The Role of Phonetics15:00
The Role of Phonetics in Recognition16:37
Annotation vs Phonetic Structure18:16
Annotation of a Sign19:32
Phonetic Structure of Signs21:16
How Expensive is Phonetic Modeling?23:38
Automatic Extraction of Phonetic Structure24:24
Training and Alignment of Phonetic SUs25:58
Phonetic Models to HMM28:08
Phonetic Subunit Training, Alignment29:07
Phonetic Sub-Units - 130:56
Phonetic Sub-Units - 232:01
Recognition based on both Data-Driven SUs + Phonetic Transcriptions33:29
Data-Driven vs. Phonetic Subunits Recognition34:01
Conclusions and The Big Picture35:52
Thank you38:02