2007 AnalysisofMorphBasedSpeechRecog

• (Creutz et al., 2007) ⇒ Mathias Creutz, Teemu Hirsimaki, Mikko Kurimo, Antti Puurula, Janne Pylkkonen, Vesa Siivola, Matti Varjokallio, Ebru Arisoy, Murat Saraclar, and Andreas Stolcke. (2007). “Analysis of Morph-Based Speech Recognition and the Modeling of Out-of-Vocabulary Words Across Languages.” In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (ACL 2007).

Subject Headings: Subword-Level Language Model; OOV Word; In-Vocabulary Word; OOV Rate; OOV Detection, Morfessor; MAP Optimization Criterion; Grapheme-To-Phoneme Mapping, Morph Language Model, Word Language Model.

Cited By

• Google Scholar: ~ 36 Citations.

Quotes

Abstract

We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four "morphologically rich" languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. By estimating n-gram LMs over sequences of morphs instead of words, better vocabulary coverage and reduced data sparsity is obtained. Standard word LMs suffer from high out-of-vocabulary (OOV) rates, whereas the morph LMs can recognize previously unseen word forms by concatenating morphs. We show that the morph LMs generally outperform the word LMs and that they perform fairly well on OOVs without compromising the accuracy obtained for in-vocabulary words.

BibTeX

@inproceedings{2007_AnalysisofMorphBasedSpeechRecog,
  author    = {Mathias Creutz and
               Teemu Hirsimaki and
               Mikko Kurimo and
               Antti Puurula and
               Janne Pylkkonen and
               Vesa Siivola and
               Matti Varjokallio and
               Ebru Arisoy and
               Murat Saraclar and
               Andreas Stolcke},
  editor    = {Candace L. Sidner and
               Tanja Schultz and
               Matthew Stone and
               ChengXiang Zhai},
  title     = {Analysis of Morph-Based Speech Recognition and the Modeling of Out-of-Vocabulary
               Words Across Languages},
  booktitle = {Proceedings of the Human Language Technology Conference of the North American Chapter
               of the Association of Computational Linguistics (ACL 2007)},
  pages     = {380--387},
  publisher = {The Association for Computational Linguistics},
  year      = {2007},
  url       = {https://www.aclweb.org/anthology/N07-1048/},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2007 AnalysisofMorphBasedSpeechRecog	Andreas Stolcke Mathias Creutz Teemu Hirsimaki Mikko Kurimo Antti Puurula Janne Pylkkonen Vesa Siivola Matti Varjokallio Ebru Arisoy Murat Saraclar			Analysis of Morph-Based Speech Recognition and the Modeling of Out-of-Vocabulary Words Across Languages						2007