Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages

Autor:	Padhi, Trideba, Biswas, Astik, De Wet, Febe, van der Westhuizen, Ewald, Niesler, Thomas
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Computation and Language Computer Science - Machine Learning Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extractor using nine Southern Bantu languages that form part of the freely available multilingual NCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features and i-vectors to train acoustic models for automatic speech recognition (ASR) in the target code-switched languages. Our results show that the inclusion of the mBNF features leads to clear performance improvements over a baseline trained without the mBNFs for code-switched English-isiZulu, English-isiXhosa, English-Sesotho and English-Setswana speech. Comment: In Proceedings of The First Workshop on Speech Technologies for Code-Switching in Multilingual Communities
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2011.03118 Zobrazit plný text záznamu View this record from Arxiv