Multilingual Bottleneck Features For Improving ASR Performance Of Code-switched Speech In Under-resourced Languages

Abstract

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 tra

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypadhi2020multilingual

Related papers

• Exploiting Cross-lingual Speaker And Phonetic Diversity For Unsupervised Subword Modeling (2019)6.77
• Semi-supervised Development Of ASR Systems For Multilingual Code-switched Speech In Under-resourced Languages (2020)0.00
• Multilingual Self-supervised Speech Representations Improve The Speech Recognition Of Low-resource African Languages With Codeswitching (2023)0.00
• Analysis Of Multilingual Sequence-to-sequence Speech Recognition Systems (2018)0.00
• Acoustic And Textual Data Augmentation For Improved ASR Of Code-switching Speech (2018)9.92
• Adaptive Activation Network For Low Resource Multilingual Speech Recognition (2022)0.00
• Semi-supervised Acoustic Model Training For Speech With Code-switching (2018)7.81
• Unified Model For Code-switching Speech Recognition And Language Identification Based On A Concatenated Tokenizer (2023)8.09