Loading [a11y]/accessibility-menu.js
Similar Word Model for Unfrequent Word Enhancement in Speech Recognition | IEEE Journals & Magazine | IEEE Xplore
Scheduled Maintenance: On Tuesday, 25 February, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (1800-2200 UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

Similar Word Model for Unfrequent Word Enhancement in Speech Recognition


Abstract:

The popular n-gram language model (LM) is weak for unfrequent words. Conventional approaches such as class-based LMs pre-define some sharing structures (e.g., word classe...Show More

Abstract:

The popular n-gram language model (LM) is weak for unfrequent words. Conventional approaches such as class-based LMs pre-define some sharing structures (e.g., word classes) to solve the problem. However, defining such structures requires prior knowledge, and the context sharing based on these structures is generally inaccurate. This paper presents a novel similar word model to enhance unfrequent words. In principle, we enrich the context of an unfrequent word by borrowing context information from some “similar words.” Compared to conventional class-based methods, this new approach offers a fine-grained context sharing by referring to words that best match the target word, and it is more flexible as no sharing structures need to be defined by hand. Experiments on a large-scale Chinese speech recognition task demonstrated that the similar word approach can improve performance on unfrequent words significantly, while keeping the performance on general tasks almost unchanged.
Page(s): 1819 - 1830
Date of Publication: 28 June 2016

ISSN Information:

Funding Agency:


References

References is not available for this document.