Name
Abstract | ||
|---|---|---|
In this paper, we develop an HMM-based sliding video text recognizer and present our results on Turkish broadcast news for the hearing impaired. We use well known speech recognition techniques to model and recognize sliding video text characters using a minimal amount of labeled data. Baseline system without any language modeling gives a word error rate of 2.2% on 138 minutes of test data. We then provide an analysis of character errors and employ a character-based language model to correct most of them. Finally we decrease the amount of training data to a quarter, split the test data into halves and investigate semi-supervised training. Word error rates after semi-supervised training are significantly lower than to those after baseline training. We see 40% relative reduction in word error rate (1.5 -> 0.9) over the test set. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ISCIS.2009.5291877 | ISCIS |
Keywords | Field | DocType |
handicapped aids,hidden Markov models,natural language processing,object recognition,speech recognition,text analysis,video signal processing,HMM-based sliding video text recognition,Turkish broadcast news,baseline system,character-based language model,hearing impaired,hidden Markov model,semi-supervised training,speech recognition techniques,word error rates | Turkish,Computer science,Word error rate,Speech recognition,Feature extraction,Natural language processing,Test data,Artificial intelligence,Hidden Markov model,Language model,Cognitive neuroscience of visual object recognition,Test set | Conference |
Citations | PageRank | References |
3 | 0.39 | 6 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Temucin Som | 1 | 3 | 0.39 |
| Dogan Can | 2 | 128 | 10.64 |
| Murat Saraclar | 3 | 669 | 62.91 |