Language modeling is a crucial component in natural language continuous speech recognition, due to the difficulty involved by continuous speech [1], [2]. Language modeling attempts to capture regularities in natural language for the purpose of improving the recognition performance. Many studies have shown that the word error rate of automatic speech recognition (ASR) systems decreases significa...

We present our recent progress in filled pause (FP) modeling for a highly spontaneous medical transcription task. Our studies confirm that FP modeling is an important topic for spontaneous speech applications, which must be explicitly addressed in acoustic, lexical, and language modeling. We provide a framework for datadriven lexical modeling of FP acoustic variability with respect to phonemic ...

We describe a series of experiments in which memorybased machine learning techniques are used for the interpretation of spoken user input in human-machine interactions. In these experiments, the task is to determine the dialogue act of the user input and the type of information slots the user fills, on the basis of a variety of features representing the spoken input (speech measurements and wor...

Spectral degradation reduces access to the acoustics of spoken language and compromises how learners break into its structure. We hypothesised that spectral degradation disrupts word segmentation, but that listeners can exploit other cues to restore detection of words. Normalhearing adults were familiarised to artificial speech that was unprocessed or spectrally degraded by noise-band vocoding ...

Performance-intensity functions for Pediatric Speech Intelligibility Test (PSI) word and sentence materials presented in competition were obtained for a set of identical female twins, aged 4 years, 2 months. Twin B had a medical history significant for recurrent otitis media, while Twin A had only one reported occurrence of the disease. Twin A yielded normal functions for both word and sentence...

Elucidating the evolution of Phlebotominae is important not only to revise their taxonomy, but also to help understand the origin of the genus Leishmania and its relationship with humans. Our study is a phenetic portrayal of this history based on the genetic relationships among some New Word and Old Word taxa. We used both multilocus enzyme electrophoresis and morphometry on 24 male specimens o...

This paper introduces a new neural structure called FusionNet, which extends existing attention approaches from three perspectives. First, it puts forward a novel concept of “history of word” to characterize attention information from the lowest word-level embedding up to the highest semantic-level representation. Second, it identifies an attention scoring function that better utilizes the “his...

Additive and interactive effects of word frequency, stimulus quality, and semantic priming have been used to test theoretical claims about the cognitive architecture of word-reading processes. Additive effects among these factors have been taken as evidence for discrete-stage models of word reading. We present evidence from linear mixed-model analyses applied to 2 lexical decision experiments i...

to complete “the use theory of meaning”, paul horwich put forward a new thesis upon which some usages of a word have explanatory role and justify the overall use-regularities of that word. these specific usages have a basic acceptance property which makes them believable in user’s belief system and, like a semantic axiom, make other usages justified. but, there are still some usages that cannot...

Today there are many languages spoken in the world, among which English is the most popular one. However, words in English evolved a lot in history such that it is very difficult for contemporary people to read ancient English articles. There are many changes, such as the mutation of word itself, the migration of word usage from one context to another, etc. It is thus very interesting to unders...