On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR
This addresses Mandarin Chinese ASR by exploiting language-specific characteristics, though it appears incremental as it builds on existing encoder-decoder frameworks.
The paper tackles Mandarin Chinese ASR by leveraging the relationship between Pinyin and characters, proposing a dual-decoder model with asynchronous decoding and fuzzy Pinyin sampling. Results on AISHELL-1 show significant improvement over strong baselines without a language model.
End-to-end automatic speech recognition (ASR) has achieved promising results. However, most existing end-to-end ASR methods neglect the use of specific language characteristics. For Mandarin Chinese ASR tasks, there exist mutual promotion relationship between Pinyin and Character where Chinese characters can be romanized by Pinyin. Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character. Furthermore, we proposed a two-stage training strategy to make training more stable and converge faster. The results on the test sets of AISHELL-1 dataset show that the proposed enhanced dual-decoder model without a language model is improved by a big margin compared to strong baseline models.