Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition
This addresses the challenge of training multilingual speech recognition systems for code-switching, which is incremental as it builds on existing end-to-end models with a novel data augmentation approach.
The paper tackles the problem of limited transcribed code-switching speech data for automatic speech recognition by proposing a data augmentation method that concatenates audio and labels from different languages, resulting in a 5.03% improvement in word error rate on unseen inter-sentential language switches.
Code-Switching (CS) is referred to the phenomenon of alternately using words and phrases from different languages. While today's neural end-to-end (E2E) models deliver state-of-the-art performances on the task of automatic speech recognition (ASR) it is commonly known that these systems are very data-intensive. However, there is only a few transcribed and aligned CS speech available. To overcome this problem and train multilingual systems which can transcribe CS speech, we propose a simple yet effective data augmentation in which audio and corresponding labels of different source languages are concatenated. By using this training data, our E2E model improves on transcribing CS speech. It also surpasses monolingual models on monolingual tests. The results show that this augmentation technique can even improve the model's performance on inter-sentential language switches not seen during training by 5,03% WER.