cs.CLNov 11, 2026

Dynamic Block-Online Streaming ASR for Low-Resource Agglutinative Code-Switching Speech with Morphology-Aware Evaluation

Authors: Kazi Rafat, Afifa Imran, Md. Ismail Hossain, Md. Romzan Ali, Fuad Rahman, Sifat Momen, Shafin Rahman, Nabeel Mohammed

Organizations: Apurba NSU R&D Lab, North South University, Dhaka, Bangladesh · Apurba Technologies, Dhaka, Bangladesh

Abstract

Low-resource, agglutinative languages challenge low-latency ASR, as fixed lookahead windows fail when grapheme order diverges, suffixes cross code-switch boundaries, or code-switching data is imbalanced. We present the first comprehensive study of streaming ASR for intra-sentential Bangla-English code-switching, identifying a mismatch between strict causal streaming and long-range morphological dependencies. We introduce a Dynamic Block-Online framework with VAD-aligned inference that balances semantics, latency, and context, enabling global bidirectional attention to preserve morphological integrity. To mitigate data scarcity, we propose Script-Anchored Loanword Injection, augmenting training text with English loanwords to model phonotactic transitions. We introduce CS-WER to diagnose switch, root, and suffix errors, and show that flexible latency budgets enhance recognition of agglutinative and mixed-language speech, with successful transfer to menstrual-medical domains.

Figures & tables

Explore similar work

CardsList
  1. Adding Robust Code-Switching Capabilities to High Performance Multilingual ASR

    Jun 20, 2026Enes Yavuz Ugan, Alexander WaibelCode-Switching Speech RecognitionCode-Switching

  2. LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR

    Oct 12, 2026Yuxuan He, Genshun Wan, Pengcheng Li +3Code-Switching Speech RecognitionMultilingual ASR

  3. Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR

    Jul 10, 2026Sanjid Hasan, Md. Abdur RahmanAutomatic Speech RecognitionLow-Resource Speech Recognition