Semi-supervised Development Of ASR Systems For Multilingual Code-switched Speech In Under-resourced Languages

Abstract

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual automatic speech recognisers (ASRs) corresponding to four different language pairs between which speakers switch frequently. The second uses a single, unified, five-lingual ASR system that represents all the languages (English, isiZulu, isiXhosa, Setswana and Sesotho). We evaluate the effectiveness of these two approaches when used to add additional data to our extremely sparse training sets. Results indicate that batch-wise semi-supervised training yields better results than a non-batch-wise approach. Furthermore, while the separate bilingual systems achieved better recognition performance than the unified system, they benefited more from pseudo-labels generated by the five-lingual system than from those generated by the bilingual systems.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybiswas2020semi

Related papers

• Multilingual Self-supervised Speech Representations Improve The Speech Recognition Of Low-resource African Languages With Codeswitching (2023)0.00
• Semi-supervised Acoustic Model Training For Speech With Code-switching (2018)7.81
• Using Heterogeneity In Semi-supervised Transcription Hypotheses To Improve Code-switched Speech Recognition (2021)0.00
• Acoustic And Textual Data Augmentation For Improved ASR Of Code-switching Speech (2018)9.92
• Multilingual Bottleneck Features For Improving ASR Performance Of Code-switched Speech In Under-resourced Languages (2020)0.00
• Leveraging Data Collection And Unsupervised Learning For Code-switched Tunisian Arabic Automatic Speech Recognition (2023)6.77
• Language Modeling For Code-switching: Evaluation, Integration Of Monolingual Data, And Discriminative Training (2018)5.24
• Semi-supervised Acoustic Modelling For Five-lingual Code-switched ASR Using Automatically-segmented Soap Opera Speech (2020)0.00