2006
DOI: 10.1016/j.csl.2005.07.002
|View full text |Cite
|
Sign up to set email alerts
|

Unlimited vocabulary speech recognition with morph language models applied to Finnish

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
100
2

Year Published

2006
2006
2016
2016

Publication Types

Select...
5
4
1

Relationship

3
7

Authors

Journals

citations
Cited by 104 publications
(102 citation statements)
references
References 34 publications
0
100
2
Order By: Relevance
“…However, in agglutinative and highly inflected languages such as Finnish [6], Turkish [12], Estonian, Hungarian and Slavic languages, a simple stemming strategy is unlikely to perform well [4,6].…”
Section: Introductionmentioning
confidence: 99%
“…However, in agglutinative and highly inflected languages such as Finnish [6], Turkish [12], Estonian, Hungarian and Slavic languages, a simple stemming strategy is unlikely to perform well [4,6].…”
Section: Introductionmentioning
confidence: 99%
“…The decoder is a time-synchronous beam-pruned Viterbi token-pass system, and the language model is a morph-based growing n-gram model (Hirsimäki et al, 2009) trained on Finnish book and newspaper data with 145 million words. The vocabulary is in practice unlimited, since all words and word forms can be represented with statistical morphs (Hirsimäki et al, 2006).…”
Section: Baseline Systemmentioning
confidence: 99%
“…On account of this, each unit could have a closer counterpart in the other language (Spanish, in this case), and then, a more accurate translations could be obtained. In (Hirsimäki et al, 2006) an unsupervised algorithm for discovering word fragments was presented and evaluated in speech recognition for Finnish. The language model based on those units offered remarkable improvements over the traditional word-based language model.…”
Section: Morphological Approachmentioning
confidence: 99%