In this paper, we propose a novel method of building a language model for open-vocabulary Korean word recognition. Due to the complex morphology of Korean, it is inappropriate to ...
The POSSLT 1 is a Korean to English spoken language translation (SLT) system. Like most other SLT systems, automatic speech recognition (ASR), machine translation (MT), and text-t...
Automatic generation of text summaries for spoken language faces the problem of containing incorrect words and passages due to speech recognition errors. This paper describes comp...
We report experimental results associated with speech-driven text retrieval, which facilitates retrieving information in multiple domains with spoken queries. Since users speak co...
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...