In this paper, we describe problems in recognizing largevocabulary Korean continuous speech, and proposed solutions to them. Korean sentences consist of eojeols, which are separated by spaces in text and consist of morphemes. When we use morpheme units, there are many word insertion and deletion errors because morpheme units are too short. We introduce a between-word phone variation lexicon tha...

Previously, phone-based and word-based approaches have been used for spoken document retrieval. The former suffers from high error rates and the latter from limited vocabulary of the recognizer. Our method relies on unlimited vocabulary continuous speech recognizer that uses morpheme-like units discovered in an unsupervised manner. The morpheme-like units, or “morphs” for short, have been succe...

We apply multi-rate HMMs, a tree structured HMM model, to the word-alignment problem. Multi-rate HMMs allow us to model reordering at both the morpheme level and the word level in a hierarchical fashion. This approach leads to better machine translation results than a morphemeaware model that does not explicitly model morpheme reordering.

We present a technique for refining a baseline segmentation and generating a plausible underlying morpheme segmentation by integrating hand-written rewrite rules into an existing state-of-the-art unsupervised morphological induction procedure. Performance on measures which consider surface-boundary accuracy and underlying morpheme consistency indicates this technique leads to improvements over ...

PURPOSE The purpose of this study was to test Bedore and Leonard's (1998) proposal that a verb morpheme composite may hold promise as a clinical marker for specific language impairment (SLI) in English speakers and serve as an accurate basis for the classification of children with and without SLI beyond the preschool level. METHOD The language transcripts of 50 school-age children with SLI (M...

Applicativization is highly productive in a language like Chichewa. The applicative affix augments the a(rgument)-structure of a verb by bringing in an additional semantic role, which is most frequently a benefactive, instrument or locative role. We show in this paper that the structure of the word can be represented in the form of a morphology-syntax interface tree, which makes it possible to ...

Words are built from smaller meaning bearing parts, called morphemes. As one word can contain multiple morphemes, one morpheme can be present in different words. The number of distinct words a morpheme can be found in is its family size. Here we used Birth-Death-Innovation Models (BDIMs) to analyze the distribution of morpheme family sizes in English and German vocabulary over the last 200 year...

This paper describes statistical analysis results of the corpus for KT{TREASURE (Korea Telecom Train ticket REservation Aid System based Upon speech REcognition). As the beginning of this development, two sets of speech corpus were collected. One was based on human-human(H-H) dialogues and the other was based on human-computer(H-C) dialogues. Wizard of Oz(WOZ) experiment was carried out to coll...