Shuji Doshita

Learn More
We propose an e cient two-pass search algorithm for LVCSR. Instead of conventional word graph, the rst preliminary pass generates \word trellis index", keeping track of all survived word hypotheses within the beam every time-frame. As it represents all found word boundaries non-deterministically, we can (1) obtain accurate sentence-dependent hypotheses on(More)
The prosodic features of lled pauses ( llers) and selfrepair are investigated with a view towards the detection of dis uencies. First, we compare the prosodic features of typical llers and their uent homonyms using read sentences of identical phoneme sequences. It is con rmed that the llers (1) have at least 2 times longer duration than their non-dis uent(More)
English-Japanese machine translation requires a large amount of structural transformations in both grammatical and conceptual level. In order to make its control structure clearer and more understandable, this paper proposes a model based on Montague Gramamr. Translation process is modeled as a data flow computation process. Formal description tools are(More)
The problem we want to handle in this p a p e r is vagueness. A notion of space, which we basically have, plays an important part in the faculty of thinking and speech. In this paper, we concentrate on a particular class of spatial descriptions, namely descriptions about positional relations on a two-dimensional space. A theoretical device we present in(More)
This 1)al)(,r drs( 'ribrs tit(' un(h,rstanding l)ro('('ss of the spatial descriptions in ,lal)anese. In order to understatt(I tlw described worhl, tit(' a, it |hors 113" to r('('Ollstru('t tit(' gc(nm,tric model of tit(' gh)bal s('en(' frmn tlw scenic descriptions drawing a spaco. It is done by an experimental ('Omlmter itrogranl SPR INT. whiclt lakes(More)