Word alignment is to estimate a lexical translation probability p(e|f), or to estimate the correspondence g(e, f) where a function g outputs either 0 or 1, between a source word f and a target word e for given bilingual sentences. In practice, this formulation does not consider the existence of ‘noise’ (or outlier) which may cause problems depending on the corpus. N -to-m mapping objects, such ...

Abstract It remains under debate whether the fusiform visual word form area (VWFA) is specific to visual word form and whether visual expertise increases its sensitivity (Xue et al., 2006; Cohen et al., 2002). The present study examined three related issues: (1) whether the VWFA is also involved in processing foreign writing that significantly differs from the native one, (2) the effect of visu...

background: noise is one of the harmful factors of industrial environments that may cause defect such as hearing defects, high blood pressure, irritation, sleep disturbances, increased respiratory rate and oxygen consumption. the residents and personnel working in industries around mehrabad airport continuously exposed to noise pollution caused by the traffic of passenger, war and training airp...

Recently, acoustic models based on deep neural notworks (DNNs) have been introduced and showed dramatic improvements over acoustic models based on GMM in a variety of tasks. In this paper, we considered the improvement of noise robustness of DNN. Inspired by Missing Feature Theory and static noise aware training, we proposed an approach that uses a noise-suppressed acoustic feature and estimate...

This paper reports on word sense disambiguation of Korean nouns with information retrieval technique. First, context vectors are constructed using contextual words in training data. Then, the words in the context vector are weighted with local density. Each sense of a target word is represented as ‘Static Sense Vector’ in word space, which is the centroid of the context vectors. Contextual nois...

In this paper, we propose an acoustic model training technique which is robust against outliers such as clipping, unexpected noise, poorly pronounced word segments, or mistranscriptions, which deteriorate the quality of the acoustic models and in turn decrease speech recognition performance. The outlier-robust acoustic model training technique is based on a maximum likelihood (ML) criterion and...

 Background: According to previous studies, most of the speech recognition disorders in older adults are the results of deficits in audibility and auditory temporal resolution. In this paper, the effect of ageing on timecompressed speech and auditory temporal resolution by word recognition in continuous and interrupted noise was studied. Methods: A time-compressed speech test (TCST) w...

Toshiba English Text-to-Speech Synthesizer utilizes several new techniques to produce synthesized speech that is more natural-sounding and intelligible than that created by conventional synthesizers. The closed-loop training method creates synthesis units that most closely resemble the training data and are the least susceptible to prosodic distortion noise by analytically solving an equation t...

PURPOSE This study examined how repeated presentations of words in noise affected understanding of both trained and untrained words in noise (in isolation and in sentences). METHOD Eight older listeners with hearing impairment completed a word-based auditory training protocol lasting approximately 12 weeks. Training materials were presented in a closed-set condition with both orthographic and...