Infants prefer to listen to happy speech. To assess influences of speech affect on early lexical processing, 7.5and 10.5-month-old infants were familiarized with one word spoken with happy affect and another with neutral affect and then tested on recognition of these words in fluent passages. Infants heard all passages either with happy affect or with neutral affect. Contrary to initial expecta...

In this paper, we investigate the use of a Recurrent Neural Network (RNN) in combining hybrid input types, namely word and pseudo-morpheme (PM) for Thai LVCSR language modeling. Similar to other neural network frameworks, there is no restriction on RNN input types. To exploit this advantage, the input vector of a proposed hybrid RNN language model (RNNLM) is a concatenated vector of word and PM...

Exploiting unlabeled text data to leverage the system performance has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Named entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. The participants of the CHEMDNER task of the BioCreative IV challenge are as...

This study was designed to assess whether the effects of computer-assisted practice on visual word recognition differed for children with reading disabilities (RD) with or without aptitude-achievement discrepancy. A sample of 73 Spanish children with low reading performance was selected using the discrepancy method, based on a standard score comparison (i.e., the difference between IQ and achie...

As an important task in biomedical text mining, biomedical named entity recognition (Bio-NER) has increasingly attracted researchers attention. Various methods have been employed to solve this problem and achieved desirable results on the annotated datasets. In this work, we focus on the feature set to reduce the training cost by feature selection and template optimization. Also, we integrate t...

In this paper, we describe a technique to improve named entity recognition in a resource-poor language (Hindi) by using cross-lingual information. We use an on-line machine translation system and a separate word alignment phase to find the projection of each Hindi word into the translated English sentence. We estimate the cross-lingual features using an English named entity recognizer and the a...

This paper deals with a problem of prosodically emphasized word detection in Czech speech. The main goal is to propose an automatic emphasized word detection system that would be component of an Automatic speech recognition system (ASR) and would enrich its text output with highlighting emphasized words. The detection method is based on Czech prosodic rules and uses speech signal intensity, pit...

Information is passed between the two systems using the Word Network (or Word Lattice) which is a set of word-score pairs together with the start and end points for each word. The word network is organized as a directed acyclic graph, whose arcs are labeled as word-score pairs, and whose nodes are moments in time. The recognition problem is to find the best scoring grammatical sequence of words...