# A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese

arXiv: https://arxiv.org/abs/1805.06239 · HTML: https://mlsanity.com/paper/1805.06239/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 10 of 10)

- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities](https://mlsanity.com/paper/2211.05756/) (2022)
- [Decoupling recognition and transcription in Mandarin ASR](https://mlsanity.com/paper/2108.01129/) (2021)
- [Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question](https://mlsanity.com/paper/2201.01209/) (2022)
- [Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition](https://mlsanity.com/paper/2102.07259/) (2021)
- [Bilingual End-to-End ASR with Byte-Level Subwords](https://mlsanity.com/paper/2205.00485/) (2022)
- [KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods](https://mlsanity.com/paper/2308.11863/) (2023)
- [Romanization Encoding For Multilingual ASR](https://mlsanity.com/paper/2407.04368/) (2024)
- [Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition](https://mlsanity.com/paper/2205.11998/) (2022)

## Abstract (arXiv)

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model. In this paper, we are concerned with modeling units on Mandarin Chinese ASR tasks using sequence-to-sequence attention-based models with the Transformer. Five modeling units are explored including context-independent phonemes (CI-phonemes), syllables, words, sub-words and characters. Experiments on HKUST datasets demonstrate that the lexicon free modeling units can outperform lexicon related modeling units in terms of character error rate (CER). Among five modeling units, character based model performs best and establishes a new state-of-the-art CER of 26.64% on HKUST datasets without a hand-designed lexicon and an extra language model integration, which corresponds to a 4.8% relative improvement over the existing best CER of 28.0% by the joint CTC-attention based encoder-decoder network.