Multilingual speech recognition for both monolingual and code-switching speech is a
challenging task. Recently, based on the Mixture of Experts (MoE), many works have made …

Neural network pruning compresses automatic speech recognition (ASR) models effectively.
However, in multilingual ASR, language-agnostic pruning may lead to severe performance …

In this work, we seek to build effective code-switched (CS) automatic speech recognition
systems (ASR) under the zero-shot set-ting where no transcribed CS speech data is …

Code-switching speech recognition (CSSR) transcribes speech that switches between
multiple languages or dialects within a single sentence. The main challenge in this task is …

Code-switching (CS) phenomenon occurs when words or phrases from different languages
are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic …

We investigate using large language models (LLMs) to generate text-only training data for
improving multilingual and code-switching automatic speech recognition (ASR) through a …

Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great
strides and exhibit excellent performance in general speech recognition. However, there …

In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified
streaming and non-streaming code-switching (CS) automatic speech recognition (ASR) …

Mixture-of-experts based models, which use language experts to extract language-specific
representations effectively, have been well applied in code-switching automatic speech …

Recently, to mitigate the confusion between different languages in code-switching (CS)
automatic speech recognition (ASR), the conditionally factorized models, such as the …