Bilingual End-to-End ASR with Byte-Level Subwords

05/01/2022
by   Liuhui Deng, et al.
0

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR). We study different representations including character-level, byte-level, byte pair encoding (BPE), and byte-level byte pair encoding (BBPE) representations, and analyze their strengths and weaknesses. We focus on developing a single end-to-end model to support utterance-based bilingual ASR, where speakers do not alternate between two languages in a single utterance but may change languages across utterances. We conduct our experiments on English and Mandarin dictation tasks, and we find that BBPE with penalty schemes can improve utterance-based bilingual ASR performance by 2 smaller number of outputs and fewer parameters. We conclude with analysis that indicates directions for further improving multilingual ASR.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset