Sciweavers

2610 search results - page 56 / 522
» The Recognition Strategy Language
Sort
View
ICDAR
2003
IEEE
14 years 3 months ago
Learning the lexicon from raw texts for open-vocabulary Korean word recognition
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 ...
Sungho Ryu, Jin Hyung Kim
NAACL
2007
13 years 11 months ago
POSSLT: A Korean to English Spoken Language Translation System
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...
Donghyeon Lee, Jonghoon Lee, Gary Geunbae Lee
ANLP
2000
148views more  ANLP 2000»
13 years 11 months ago
Minimizing Word Error Rate in Textual Summaries of Spoken Language
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...
Klaus Zechner, Alex Waibel
CORR
2002
Springer
118views Education» more  CORR 2002»
13 years 9 months ago
Language Modeling for Multi-Domain Speech-Driven Text Retrieval
We report experimental results associated with speech-driven text retrieval, which facilitates retrieving information in multiple domains with spoken queries. Since users speak co...
Katunobu Itou, Atsushi Fujii, Tetsuya Ishikawa
ICASSP
2010
IEEE
13 years 10 months ago
Recognition of phonemes and words in singing
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...
Annamaria Mesaros, Tuomas Virtanen