Unlimited vocabulary speech recognition with morph language models applied to Finnish Export

@article{citeulike:2072332, abstract = {In the speech recognition of highly inflecting or compounding languages, the traditional word-based language modeling is problematic. As the number of distinct word forms can grow very large, it becomes difficult to train language models that are both effective and cover the words of the language well. In the literature, several methods have been proposed for basing the language modeling on sub-word units instead of whole words. However, to our knowledge, considerable improvements in speech recognition performance have not been reported. In this article, we present a language-independent algorithm for discovering word fragments in an unsupervised manner from text. The algorithm uses the Minimum Description Length principle to find an inventory of word fragments that is compact but models the training text effectively. Language modeling and speech recognition experiments show that n-gram models built over these fragments perform better than n-gram models based on words. In two Finnish recognition tasks, relative error rate reductions between 12\% and 31\% are obtained. In addition, our experiments suggest that word fragments obtained using grammatical rules do not outperform the fragments discovered from text. We also present our recognition system and discuss how utilizing fragments instead of words affects the decoding process.}, author = {Hirsimaki, Teemu and Creutz, Mathias and Siivola, Vesa and Kurimo, Mikko and Virpioja, Sami and Pylkkonen, Janne}, citeulike-article-id = {2072332}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.csl.2005.07.002}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B6WCW-4H09XJ2-1/2/4a495d6b45f046d9d0b74389b4914689}, doi = {10.1016/j.csl.2005.07.002}, journal = {Computer Speech \& Language}, keywords = {finnish}, month = {October}, number = {4}, pages = {515--541}, posted-at = {2009-01-07 17:01:17}, priority = {2}, title = {Unlimited vocabulary speech recognition with morph language models applied to Finnish}, url = {http://dx.doi.org/10.1016/j.csl.2005.07.002}, volume = {20}, year = {2006} }

TY - JOUR ID - citeulike:2072332 L3 - citeulike-article-id:2072332 N2 - In the speech recognition of highly inflecting or compounding languages, the traditional word-based language modeling is problematic. As the number of distinct word forms can grow very large, it becomes difficult to train language models that are both effective and cover the words of the language well. In the literature, several methods have been proposed for basing the language modeling on sub-word units instead of whole words. However, to our knowledge, considerable improvements in speech recognition performance have not been reported. In this article, we present a language-independent algorithm for discovering word fragments in an unsupervised manner from text. The algorithm uses the Minimum Description Length principle to find an inventory of word fragments that is compact but models the training text effectively. Language modeling and speech recognition experiments show that n-gram models built over these fragments perform better than n-gram models based on words. In two Finnish recognition tasks, relative error rate reductions between 12% and 31% are obtained. In addition, our experiments suggest that word fragments obtained using grammatical rules do not outperform the fragments discovered from text. We also present our recognition system and discuss how utilizing fragments instead of words affects the decoding process. IS - 4 JF - Computer Speech & Language EP - 541 TI - Unlimited vocabulary speech recognition with morph language models applied to Finnish VL - 20 SP - 515 KW - finnish AU - Hirsimaki, Teemu AU - Creutz, Mathias AU - Siivola, Vesa AU - Kurimo, Mikko AU - Virpioja, Sami AU - Pylkkonen, Janne PY - 2006/10// UR - http://dx.doi.org/10.1016/j.csl.2005.07.002 ER -