Please use this identifier to cite or link to this item:
https://doi.org/10.1006/csla.1998.0118
DC Field | Value | |
---|---|---|
dc.title | Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition | |
dc.contributor.author | GuoDong, Z. | |
dc.contributor.author | KimTeng, L. | |
dc.date.accessioned | 2013-07-04T07:48:39Z | |
dc.date.available | 2013-07-04T07:48:39Z | |
dc.date.issued | 1999 | |
dc.identifier.citation | GuoDong, Z.,KimTeng, L. (1999). Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition. Computer Speech and Language 13 (2) : 125-141. ScholarBank@NUS Repository. <a href="https://doi.org/10.1006/csla.1998.0118" target="_blank">https://doi.org/10.1006/csla.1998.0118</a> | |
dc.identifier.issn | 08852308 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/39748 | |
dc.description.abstract | While n-gram modeling is simple and dominant in speech recognition, it can only capture the short-distance context dependency within an n-word window where currently the largest practical n for natural language is three. However, many of the context dependencies in natural language occur beyond a three-word window. This paper proposes a new language modeling approach to capture the preferred relationships between words over a short or long distance through the concept of MI-Trigger pairs. Different MI-Trigger-based models are constructed in either a distance-dependent or a distance-independent way within a window from 1 to 10 words. This new MI-Trigger-based modeling is also compared and merged with word bigram modeling. It is found that the MI-Trigger-based modeling has better performance than word bigram modeling. It is also found that n-gram and MI-Trigger models have good complementarity and their proper merging can further increase the recognition rate when tested on Mandarin speech recognition. One advantage of MI-Trigger-based modeling is that the number of parameters needed for MI-Trigger modeling is much less than that of word bigram modeling. Another advantage is that the number of trigger pairs in an MI-Trigger model can be kept to a reasonable size without losing too much of its modeling power. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1006/csla.1998.0118 | |
dc.source | Scopus | |
dc.type | Article | |
dc.contributor.department | COMPUTER SCIENCE | |
dc.description.doi | 10.1006/csla.1998.0118 | |
dc.description.sourcetitle | Computer Speech and Language | |
dc.description.volume | 13 | |
dc.description.issue | 2 | |
dc.description.page | 125-141 | |
dc.description.coden | CSPLE | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.