Simulated confusions enable the use of large text-only corpora for discriminative language modeling by hallucinating the likely.

In this paper, we extend the phrasal cohort technique to the fully unsupervised scenario, where transcribed data are completely absent. Experimental results ...

In [7] the authors bypassed the phonetic confusion modeling and extended the phrasal cohort approach, which was previously applied only on transcribed data [8], ...

Phrasal cohort based unsupervised discriminative language modeling. Xu P., Roark B., Khudanpur S. Expand. Publication type: Proceedings Article. Publication ...

This study proposes three ways to determine a sequence that could serve as the missing reference text and two approaches which use this information to ...

Discriminative language modeling aims to reduce the error rates by rescoring the output of an automatic speech recognition (ASR) system. Discriminative language ...

Discriminative language modeling (DLM) aims to choose the most accurate word sequence by reranking the alternatives out-.

ABSTRACT. This paper investigates semi-supervised methods for discriminative language modeling, whereby n-best lists are “hallucinated” for given.

We propose three target output selection methods for unsupervised DLM training.Ranking perceptron performs better than structured perceptron in most cases.

One way to improve the accuracy of auto- matic speech recognition (ASR) is to use dis- criminative language modeling (DLM), which.