dc.citation.conferencePlace |
US |
- |
dc.citation.conferencePlace |
Miami, FL |
- |
dc.citation.endPage |
124 |
- |
dc.citation.startPage |
119 |
- |
dc.citation.title |
Automatic Speech Recognition and Understanding/Spoken Language Technology |
- |
dc.contributor.author |
Kim, Taehwan |
- |
dc.contributor.author |
Livescu, Karen |
- |
dc.contributor.author |
Shakhnarovich, Gregory |
- |
dc.date.accessioned |
2023-12-20T01:37:52Z |
- |
dc.date.available |
2023-12-20T01:37:52Z |
- |
dc.date.created |
2021-09-01 |
- |
dc.date.issued |
2012-12 |
- |
dc.description.abstract |
We study the recognition of fingerspelling sequences in American Sign Language from video using tandem-style models, in which the outputs of multilayer perceptron (MLP) classifiers are used as observations in a hidden Markov model (HMM)-based recognizer. We compare a baseline HMM-based recognizer, a tandem recognizer using MLP letter classifiers, and a tandem recognizer using MLP classifiers of phonological features. We present experiments on a database of fingerspelling videos. We find that the tandem approaches outperform an HMM-based baseline, and that phonological feature-based tandem models outperform letter-based tandem models. |
- |
dc.identifier.bibliographicCitation |
Automatic Speech Recognition and Understanding/Spoken Language Technology, pp.119 - 124 |
- |
dc.identifier.doi |
10.1109/SLT.2012.6424208 |
- |
dc.identifier.scopusid |
2-s2.0-84874284869 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/53841 |
- |
dc.language |
영어 |
- |
dc.publisher |
IEEE |
- |
dc.title |
American sign language fingerspelling recognition with phonological feature-based tandem models |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2012-12-02 |
- |