A unified language model for large vocabulary continuous speech recognition of Turkish

Authors:
Ebru Arisoy;Helin Dutaǧaci;Levent M. Arslan
Affiliations:
Electrical and Electronic Engineering Department, Boǧaziçi University, Bebek, Istanbul, Turkey;Electrical and Electronic Engineering Department, Boǧaziçi University, Bebek, Istanbul, Turkey;Electrical and Electronic Engineering Department, Boǧaziçi University, Bebek, Istanbul, Turkey
Venue:
Signal Processing - Fractional calculus applications in signals and systems
Year:
2006

Citing 9
Cited 3

Error-tolerant finite-state recognition with applications to morphological analysis and spelling correction

Computational Linguistics
Statistical methods for speech recognition

Statistical methods for speech recognition
The Cambridge University Multimedia Document Retrieval demo system (demonstration session)

SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Korean large vocabulary continuous speech recognition with morpheme-based recognition units

Speech Communication
Mostly-unsupervised statistical segmentation of Japanese: applications to kanji

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Spelling correction in agglutinative languages

ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Statistical morphological disambiguation for agglutinative languages

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
An Introduction to Language

An Introduction to Language

Morph-based speech recognition and modeling of out-of-vocabulary words across languages

ACM Transactions on Speech and Language Processing (TSLP)
Morpheme-Based Automatic Speech Recognition of Basque

IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis
Automatic speech recognition for under-resourced languages: A survey

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have designed a Turkish dictation system for newspaper content transcription application. Turkish is an agglutinative language with free word order. These characteristics of the language result in vocabulary explosion, large number of out-of-vocabulary (OOV) words and an increased complexity of n-gram language models in speech recognition when words are used as recognition units. In this paper, alternative language modeling units like "stems and endings", "stems and morphemes", and "syllables" are investigated instead of "words". These recognition units are compared in terms of vocabulary size, coverage, bigram perplexity and speech recognition performance. A combined model is proposed which aims to produce a balance between the OOV rate and the amount of phoneme sequence constraints on recognition units. The proposed model resulted in letter error rates (LER's) of approximately 28% for a speaker independent system and 20% for a speaker dependent system. These error rates are smaller compared to the traditional word-based model for newspaper content transcription application.