Web-based possibilistic language models for automatic speech recognition

Oger, Stanislas; Linarès, Georges

doi:10.1016/j.csl.2014.02.003

Cited by 4 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, the only language model based on the possibility theory is the one described in [18]. This work uses the web as an open training corpus to improve language modeling.…”

Section: Related Workmentioning

confidence: 99%

“…The basic idea behind the method of Oger and Linarès [18] is to consider the observed events and non-observed ones in the web. Therefore, two theories were employed: probability and possibility.…”

Section: Related Workmentioning

confidence: 99%

“…To benefit from both theories: probability and possibility, Oger and Linarès [18] also proposed a method to combine the probability and the possibility measures.…”

Section: Related Workmentioning

confidence: 99%

“…The method proposed by Oger and Linarès [18] estimates the possibility of a word-sequence from the web or from a text corpus. The basic idea of this method is the following: for a given word-sequence, the possibility is estimated according to its sub-sequences.…”

Section: Possibility Estimated On a Text Corpusmentioning

confidence: 99%

“…This paper is organized as follows: the next section briefly presents the probabilistic n-gram language models, followed by a description of the possibility theory and the motivation that encouraged us to use it. Then, the only work, in our knowledge, that has been done to model a possibilistic language model [18] is presented. Finally, we present and describe the language model based on the possibility theory along with some tests to compare its performances with those of the baseline language models.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A New Language Model Based on Possibility Theory

Menacer

Boumerdas

Zakaria

et al. 2018

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Language modeling is a very important step in several NLP applications. Most of the current language models are based on probabilistic methods. In this paper, we propose a new language modeling approach based on the possibility theory. Our goal is to suggest a method for estimating the possibility of a word-sequence and to test this new approach in a machine translation system. We propose a wordsequence possibilistic measure, which can be estimated from a corpus. We proceeded in two ways: first, we checked the behavior of the new approach compared with the existing work. Second, we compared the new language model with the probabilistic one used in statistical MT systems. The results, in terms of the METEOR metric, show that the possibilistic-language model is better than the probabilistic one. However, in terms of BLEU and TER scores, the probabilistic model remains better.

show abstract

“…To our knowledge, the only language model based on the possibility theory is the one described in [18]. This work uses the web as an open training corpus to improve language modeling.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…To benefit from both theories: probability and possibility, Oger and Linarès [18] also proposed a method to combine the probability and the possibility measures.…”

Section: Related Workmentioning

confidence: 99%

Section: Possibility Estimated On a Text Corpusmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A New Language Model Based on Possibility Theory

Menacer

Boumerdas

Zakaria

et al. 2018

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

show abstract

Ameliorated language modelling for lecture speech recognition of Indian English

Phull

Kumar

2018

Sādhanā

View full text Add to dashboard Cite

A great amount of research is growing towards the automatic transcription of lectures that consist of numerous information and knowledge that could be helpful to the educational systems and institutes. In large vocabulary speech recognition, language model plays a paramount role in reducing the humongous search space. However, language modelling is very brittle when moving from one domain to another or when moving from read speech to spontaneous speech. Also, lecture speech recognition will have some of the characteristics of spontaneous speech. Hence, it is very challenging to build the language model for this task. In this paper, a judicious approach to adapt the language model in a way where the language model will be in close proximity to the topic spoken in the lecture speech has been depicted. The evaluation of the language model is devised using the proposed approach with the existing language models such as CMU Sphinx, Gigaword and HUB-4. We observed the results analysis that the language models devised from the proposed approach outperform from the existing language models in terms of word error rate, perplexity and out of vocabulary rate. Analysis shows that the presented two-phase approach has resulted in an average decrease of the word error rate to be approximately 14% and the perplexity is decreased by half on average.

show abstract

Analyzing various topic modeling approaches for Domain-Specific language model

Phull

Kumar

2017

2017 International Conference on Networks &Amp; Advances in Computational Technologies (NetACT)

View full text Add to dashboard Cite

Web-based possibilistic language models for automatic speech recognition

Cited by 4 publications

References 22 publications

A New Language Model Based on Possibility Theory

A New Language Model Based on Possibility Theory

Ameliorated language modelling for lecture speech recognition of Indian English

Analyzing various topic modeling approaches for Domain-Specific language model

Contact Info

Product

Resources

About