Efficient large vocabulary continuous speech recognition of morphologically rich languages is a big challenge due to the rapid vocabulary growth. To improve the results various subword units called as morphs are applied as basic language elements. The improvements over the word baseline, however, are changing from negative to error rate halving across languages and tasks. In this paper we make ...

Although the size of a child's vocabulary associates with language-processing skills, little is understood regarding how this relation emerges. This investigation asks whether and how the structure of vocabulary knowledge affects language processing in English-learning 24-month-old children (N = 32; 18 F, 14 M). Parental vocabulary report was used to calculate semantic density in several early-...

State-of-the-art multilingual ontology matchers use machine translation to reduce the problem to the monolingual case. We investigate an alternative, self-contained solution based on semantic matching where labels are parsed by multilingual natural language processing and then matched using a language-independent knowledge base acting as an interlingua. As the method relies on the availability ...

We present a conversational telephone speech data set designed to support research on novel acoustic models. Small vocabulary tasks from 10 words up to 500 words are defined using subsets of the Switchboard-1 corpus; each task has a completely closed vocabulary (an OOV rate of 0%). We justify the need for these tasks, describe the algorithm for selecting them from a large corpus, give a statist...

Phonologically constrained morphological analysis (PCMA) is the decomposition of words into their component morphemes conditioned by both orthography and pronunciation. This article describes PCMA and its application in large-vocabulary continuous speech recognition to enhance recognition performance in some tasks. Our experiments, based on the British National Corpus and the LOB Corpus for tra...

Many important speech recognition tasks feature an open, constantly changing vocabulary. (E.g. broadcast news transcription, spoken document retrieval, . . . ) Recognition of (new) words requires acoustic baseforms for them to be known. Commonly words are transcribed manually, which poses a major burden on vocabulary adaptation and interdomain portability. In this work we investigate the possib...

The present study investigated whether word learning and retention in a second language are contingent upon a task's involvement load, i.e., the amount of need, search, and evaluation the task imposes. Laufer and Hulstijn (2001) contend that tasks with higher degrees of these three components induce higher involvement load, and are, therefore, more effective for word learning. To test this clai...

In this paper, we have successfully extended our previous work of convex optimization methods to MMIE-based discriminative training for large vocabulary continuous speech recognition. Specifically, we have re-formulated the MMIE training into a second order cone programming (SOCP) program using some convex relaxation techniques that we have previously proposed. Moreover, the entire SOCP formula...