Variable n-grams and extensions for conversational speech language modeling Export

@article{citeulike:4006506, abstract = {Recent progress in variable n-gram language modeling provides an efficient representation of n-gram models and makes training of higher order n grams possible. We apply the variable n-gram design algorithm to conversational speech, extending the algorithm to learn skips and context-dependent classes to handle conversational speech characteristics such as filler words, repetitions, and other disfluencies. Experiments show that using the extended variable n-gram results in a language model that captures 4-gram context with less than half the parameters of a standard trigram while also improving the test perplexity and recognition accuracy}, author = {Siu, Manhung and Ostendorf, M.}, booktitle = {Speech and Audio Processing, IEEE Transactions on}, citeulike-article-id = {4006506}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/89.817454}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=817454}, doi = {10.1109/89.817454}, journal = {Speech and Audio Processing, IEEE Transactions on}, keywords = {ngram, variable}, number = {1}, pages = {63--75}, posted-at = {2009-10-03 01:25:59}, priority = {0}, title = {Variable n-grams and extensions for conversational speech language modeling}, url = {http://dx.doi.org/10.1109/89.817454}, volume = {8}, year = {2000} }

TY - JOUR ID - citeulike:4006506 L3 - citeulike-article-id:4006506 N2 - Recent progress in variable n-gram language modeling provides an efficient representation of n-gram models and makes training of higher order n grams possible. We apply the variable n-gram design algorithm to conversational speech, extending the algorithm to learn skips and context-dependent classes to handle conversational speech characteristics such as filler words, repetitions, and other disfluencies. Experiments show that using the extended variable n-gram results in a language model that captures 4-gram context with less than half the parameters of a standard trigram while also improving the test perplexity and recognition accuracy IS - 1 JF - Speech and Audio Processing, IEEE Transactions on EP - 75 TI - Variable n-grams and extensions for conversational speech language modeling VL - 8 T2 - Speech and Audio Processing, IEEE Transactions on SP - 63 KW - ngram KW - variable AU - Siu, Manhung AU - Ostendorf, M PY - 2000/// UR - http://dx.doi.org/10.1109/89.817454 ER -