Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …

Code-switching speech refers to a means of expression by mixing two or more languages
within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) …

Code-switching (CS) is common in daily conversations where more than one language is
used within a sentence. The difficulties of CS speech recognition lie in alternating languages …

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 …

Transfer learning is a common method to improve the performance of the model on a target
task via pre-training the model on pretext tasks. Different from the methods using …

Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-
switching recognition task thanks to its inherent property that present output token being …

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

Abstract Out-of-vocabulary (OOV) is a common problem for end-to-end (E2E) ASR. For code-
switching (CS), the OOV problem on the embedded language is further aggravated and …

Connectionist Temporal Classification (CTC) loss has become widely used in sequence
modeling tasks such as Automatic Speech Recognition (ASR) and Handwritten Text …

We introduce romanization encoding for script-heavy languages to optimize multilingual and
code-switching Automatic Speech Recognition (ASR) systems. By adopting romanization …