.png){kind=icon}
.png){kind=icon}
Return
Getting more from automatic transcripts for semi-supervised language modeling
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2015.08.007.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Many under-resourced languages such as Arabic diglossia or Hindi sub-dialects do not have sufficient in-domain text to build strong language models for use with automatic speech recognition (ASR). Semi-supervised language modeling uses a speech-to-text system to produce automatic transcripts from a large amount of in-domain audio typically to augment a small amount of manual transcripts. In contrast to the success of semi-supervised acoustic modeling, conventional language modeling techniques have provided only modest gains. This paper first explains the limitations of back-off language models due to their dependence on long-span n-grams, which are difficult to accurately estimate from automatic transcripts. From this analysis, we motivate a more robust use of the automatic counts as a prior over the estimated parameters of a log-linear language model. We demonstrate consistent gains for semi-supervised language models across a range of low-resource conditions. (C) 2015 Elsevier Ltd. All rights reserved.
Keywords:
Language modeling
Automatic speech recognition
LVCSR
Low-resource
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
3.4
Papers:
1.5K
Citations:
2.6K