Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11779/1572
Title: | Improving the Usage of Subword-Based Units for Turkish Speech Recognition | Other Titles: | Türkçe konuşma tanıma için sözcük altı birimlerin kullanımının iyileştirilmesi | Authors: | Çetinkaya, Gözde Saraçlar, Murat Arısoy, Ebru |
Keywords: | Konuşma tanıma Language modelling Acoustic modelling Speech recognition Akustik modelleme Dil modelleme |
Publisher: | IEEE | Source: | G. Çetinkaya, E. Arısoy and M. Saraçlar, (5-7 Oct. 2020). Improving the Usage of Subword-Based Units for Turkish Speech Recognition, 2020 28th Signal Processing and Communications Applications Conference (SIU), pp. 1-4, doi: 10.1109/SIU49456.2020.9302043. | Abstract: | Subword units are often utilized to achieve better performance in speech recognition because of the high number of observed words in agglutinative languages. In this study, the proper use of subword units is explored in recognition by a reconsideration of details such as silence modeling and position-dependent phones. A modified lexicon by finite-state transducers is implemented to represent the subword units correctly. Also, we experiment with different types of word boundary markers and achieve the best performance by adding a marker both to the left and right side of a subword unit. In our experiments on a Turkish broadcast news dataset, the subword models do outperform word-based models and naive subword implementations. Results show that using proper subword units leads to a relative word error rate (WER) reductions, which is 2.4%, compared with the word level automatic speech recognition (ASR) system for Turkish. | URI: | https://doi.org/10.1109/SIU49456.2020.9302043 https://hdl.handle.net/20.500.11779/1572 |
ISBN: | 9781728172064 | ISSN: | 2165-0608 |
Appears in Collections: | Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Improving_the_Usage_of_Subword-Based_Units_for_Turkish_Speech_Recognition.pdf Until 2040-01-01 | Proceedings Paper | 224.35 kB | Adobe PDF | View/Open Request a copy |
CORE Recommender
SCOPUSTM
Citations
2
checked on Nov 23, 2024
WEB OF SCIENCETM
Citations
1
checked on Nov 23, 2024
Page view(s)
30
checked on Nov 25, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.