Balanced End-to-end Monolingual Pre-training For Low-resourced Indic Languages Code-switching Speech Recognition

Abstract

The success in designing Code-Switching (CS) ASR often depends on the availability of the transcribed CS resources. Such dependency harms the development of ASR in low-resourced languages such as Bengali and Hindi. In this paper, we exploit the transfer learning approach to design End-to-End (E2E) CS ASR systems for the two low-resourced language pairs using different monolingual speech data and a small set of noisy CS data. We trained the CS-ASR, following two steps: (i) building a robust bilingual ASR system using a convolution-augmented transformer (Conformer) based acoustic model and n-gram language model, and (ii) fine-tuned the entire E2E ASR with limited noisy CS data. We tested our method on MUCS 2021 challenge and achieved 3rd place in the CS track. We then tested the proposed method using noisy CS data released for Hindi-English and Bengali-English pairs in Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages (MUCS 2021) and achieved 3rd place in t

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhussein2021balanced

Related papers

• End-to-end Code-switching ASR For Low-resourced Language Pairs (2019)9.76
• End-to-end ASR For Code-switched Hindi-english Speech (2019)0.00
• Language-agnostic Code-switching In Sequence-to-sequence Speech Recognition (2022)0.00
• Unified Model For Code-switching Speech Recognition And Language Identification Based On A Concatenated Tokenizer (2023)8.09
• On The End-to-end Solution To Mandarin-english Code-switching Speech Recognition (2018)12.10
• Integrating Knowledge In End-to-end Automatic Speech Recognition For Mandarin-english Code-switching (2021)5.24
• Towards End-to-end Code-switching Speech Recognition (2018)0.00
• Exploring Retraining-free Speech Recognition For Intra-sentential Code-switching (2021)5.84