For extended periods of time, sequence generation models rely on beam search as the decoding algorithm. However, the performance of beam search degrades when the model is over-confident about a suboptimal prediction. In this work, we enhance beam search by performing minimum Bayes-risk (MBR) decoding for some extra steps at a later stage. In our experiments, we found that the conventional MBR r...

The paper addresses a new evaluation measure of automatic speech recognition (ASR) and a decoding strategy oriented for speech-based information retrieval (IR). Although word error rate (WER), which treats all words in a uniform manner, has been widely used as an evaluation measure of ASR, significance of words are different in speech understanding or IR. In this paper, we define a new ASR eval...

Genetic risk prediction is an important component of individualized medicine, but prediction accuracies remain low for many complex diseases. A fundamental limitation is the sample sizes of the studies on which the prediction algorithms are trained. One way to increase the effective sample size is to integrate information from previously existing studies. However, it can be difficult to find ex...

This paper extends the minimum Bayes-risk framework to incorporate a loss function specific to the task and the ASR system. The errors are modeled as a noisy channel and the parameters are learned from the data. The resulting loss function is used in the risk criterion for decoding. Experiments on a large vocabulary conversational speech recognition system demonstrate significant gains of about...

We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functions that measure translation performance. We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, and syntactic...

Minimum Bayes Risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders in the context of Nbest list rescoring and A search over recognition lattices. Segmental MBR (SMBR) procedures have been developed to simplify implementation of MBR recognizers, by segmenting the N-best list or lattice, to reduce the size of the...

this article examines statistical inference for  where and are independent but not identically distributed pareto of the first kind (pareto (i)) random variables with same scale parameter but different shape parameters. the maximum likelihood, uniformly minimum variance unbiased and bayes estimators with gamma prior are used for this purpose. simulation studies which compare the estimators are ...

The minimum Bayes risk (MBR) criterion has previously been applied to the task of speaker adaptation in large vocabulary continuous speech recognition. The success of unsupervised MBR speaker adaptation, however, has been limited by the accuracy of the estimated transcription of the acoustic data. This paper addresses this issue not by improving the accuracy of the estimated transcription but v...

Modern automatic speech recognition (ASR) systems use statistical models of spoken language. These models are typically learned from corpora comprising many hours of transcribed speech. While a variety of machine learning approaches have been applied to this learning task, the optimal learning strategy is unknown. This thesis focusses upon a relatively recent and successful approach, the applic...