Title | Using Dependency Grammar Features in Whole Sentence Maximum Entropy Language Model for Speech Recognition |
Publication Type | Conference Paper |
Year of Publication | 2010 |
Authors | Ruokolainen T, Alumäe T, Dobrinkat M |
Conference Name | The Fourth International Conference Baltic HLT 2010 |
Publisher | IOS Press |
Conference Location | Amsterdam, The Netherlands |
ISBN Number | 978-1-60750-640-9 |
Abstract | In automatic speech recognition, the standard choice for a language model is the well-known n-gram model. The n-grams are used to predict the probability of a word given its n-1 preceding words. However, the n-gram model is not able to explicitly learn grammatical relations of the sentence. In the present work, in order to augment the n-gram model with grammatical features, we apply the Whole Sentence Maximum Entropy framework. The grammatical features are head-modifier relations between pairs of words, together with the labels of the relationships, obtained with the dependency grammar. We evaluate the model in a large vocabulary speech recognition task with Wall Street Journal speech corpus. The results show a substantial improvement in both test set perplexity and word error rate. |
URL | http://www.pinview.eu/files/Ruokolainen2010.pdf |
- Log in or register to post comments
- Google Scholar