Deep learning based large vocabulary continuous speech recognition of an under-resourced language Bangladeshi Bangla

Research in corpus-driven Automatic Speech Recognition (ASR) is advancing rapidly towards building a robust Large Vocabulary Continuous Speech Recognition (LVCSR) system. Under-resourced languages like Bangla require benchmarking large corpora for more research on LVCSR to tackle their limitations a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Acoustical Science and Technology 2021/09/01, Vol.42(5), pp.252-260
Hauptverfasser:	Samin, Ahnaf Mozib, Kobir, M. Humayon, Kibria, Shafkat, Rahman, M. Shahidur
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Automatic speech recognition Bangladeshi Bangla Bengali Continuous speech Convolutional neural network Corpus analysis Corpus linguistics Deep learning Error analysis Language modeling Large vocabulary continuous speech recognition Machine learning Mass media Morphology N-Gram language models Neural networks Quality assessment Recurrent neural network Recurrent neural networks Speech recognition Voice recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!