Sentence lipreading using hidden Markov model with integrated grammar

被引：1

作者：

Yu, K ^{[1
]}

Jiang, XY ^{[1
]}

Bunke, H ^{[1
]}

机构：

[1] Univ Bern, Dept Comp Sci, CH-3012 Bern, Switzerland

来源：

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE | 2001年 / 15卷 / 01期

关键词：

lip reading; sentence; grammar; HMM;

D O I：

10.1142/S0218001401000770

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we describe a systematic approach to the lipreading of whole sentences. A vocabulary of elementary words is considered. Based on the vocabulary, we define a grammar that generates a set of legal sentences. Our lipreading approach is based on a combination of the grammar with hidden Markov models (HMMs). Two different experiments were conducted. In the first experiment a set of e-mail commands is considered, while the set of sentences in the second experiment is given by all English integer numbers up to one million. Both experiments showed promising results, regarding the difficulty of the considered task.

引用

页码：161 / 176

页数：16

共 20 条

[1]

BAHL LR, 1990, READINGS SPEECH RECO, P332

[2]

BENOIT C, 1996, SPEECHREADING HUMANS, P351

[3]

BREGLER C, 1993, P IEEE INT C NEUR NE, P667

[4]

BROOKE NM, 1996, SPEECHREADING HUMANS, P351

[5]

BUNKE H, 1990, SYNTACTIC STRUCTURAL, P29

[6]

DALTON B, 1996, SPEECH READING HUMAN, P331

[7]

GOLDSCHEN AJ, 1995, P 28 ANN AS C SIGN S, P572

[8]

Kaufmann G, 1997, PROC INT CONF DOC, P1097, DOI 10.1109/ICDAR.1997.620678

[9]

KAUFMANN G, 1997, PROGR HANDWRITING RE, P21

[10] Speechreading using probabilistic models [J].

Luettin, J ;

Thacker, NA .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 65 (02) :163-178

← 1 2 →