Improving the Usage of Subword-Based Units for Turkish Speech Recognition Turkce Konusma Tanima icin Sozcuk Alti Birimlerin Kullaniminin Iyilestirilmesi
28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Türkiye, 5 - 07 Ekim 2020, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu49456.2020.9302043
- Basıldığı Şehir: Gaziantep
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: acoustic modelling, language modelling, speech recognition
- Boğaziçi Üniversitesi Adresli: Evet
Özet
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 positiondependent phones. A modied lexicon by nite-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 wordbased 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.