2016
DOI: 10.1016/j.specom.2016.07.004
|View full text |Cite
|
Sign up to set email alerts
|

Semi-supervised and unsupervised discriminative language model training for automatic speech recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 13 publications
0
7
0
Order By: Relevance
“…our claim of rapid adaptability of the system to varying mismatched acoustic and linguistic conditions. The extreme mismatched conditions involved in our experiments supports the possibility of going one step further and training our system on artificially generated data of noisy transformations of phrases as in [35,36,38,57–59]. Thus possibly eliminating the need for an ASR for training purposes.…”
Section: Resultsmentioning
confidence: 58%
“…our claim of rapid adaptability of the system to varying mismatched acoustic and linguistic conditions. The extreme mismatched conditions involved in our experiments supports the possibility of going one step further and training our system on artificially generated data of noisy transformations of phrases as in [35,36,38,57–59]. Thus possibly eliminating the need for an ASR for training purposes.…”
Section: Resultsmentioning
confidence: 58%
“…It should be noticed that the lack of textual corpus is also a major challenge when training language models. To address this problem, various of methods have been carried out to expand corpus in the past decade [28,29,30]. In addition, textual level transfer learning strategy by merging a pre-trained representation to the decoder is also explored.…”
Section: Introductionmentioning
confidence: 99%
“…The two steps here are conducted iteratively: (a) a Criticizing Language Model (CLM) is trained to evaluate the quality score given a text sequence, and (b) and ASR model is trained to minimize the sequence loss calculated with ground truth while maximizing the scores given by CLM. 16,17] have been developed to address such problem by involving unpaired text data (which are relatively easy to obtain) in the training progress. One approach is to utilize unpaired text data to produce a separately trained language model (LM) to rescore the output of the end-to-end approach [18,13,19,20], but at the price of extra computation during testing.…”
Section: Introductionmentioning
confidence: 99%