{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:34:22Z","timestamp":1775280862610,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3233\/978-1-60750-641-6-73","type":"book-chapter","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:27:05Z","timestamp":1740133625000},"source":"Crossref","is-referenced-by-count":1,"title":["Using Dependency Grammar Features in Whole Sentence Maximum Entropy Language Model for Speech Recognition"],"prefix":"10.3233","author":[{"family":"Ruokolainen Teemu","sequence":"additional","affiliation":[]},{"family":"Alum&auml;e Tanel","sequence":"additional","affiliation":[]},{"family":"Dobrinkat Marcus","sequence":"additional","affiliation":[]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Human Language Technologies &amp;ndash; The Baltic Perspective"],"original-title":[],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:49:23Z","timestamp":1740134963000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospressISSNISBN&issn=0922-6389&volume=219&spage=73"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/978-1-60750-641-6-73","relation":{},"ISSN":["0922-6389"],"issn-type":[{"value":"0922-6389","type":"print"}],"subject":[],"published":{"date-parts":[[2010]]}}}