# Korean Tokenization for Beam Search Rescoring in Speech Recognition

arXiv: https://arxiv.org/abs/2203.03583 · HTML: https://mlsanity.com/paper/2203.03583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 22 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/1908.10992/) (2019)
- [SpecAugment on Large Scale Datasets](https://mlsanity.com/paper/1912.05533/) (2019)
- [An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks](https://mlsanity.com/paper/2010.02534/) (2020)
- [Comparison of Decoding Strategies for CTC Acoustic Models](https://mlsanity.com/paper/1708.04469/) (2017)
- [ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers](https://mlsanity.com/paper/2004.09367/) (2020)
- [Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models](https://mlsanity.com/paper/2107.09428/) (2021)
- [Character-Level Incremental Speech Recognition with Recurrent Neural Networks](https://mlsanity.com/paper/1601.06581/) (2016)
- [Open Korean Corpora: A Practical Report](https://mlsanity.com/paper/2012.15621/) (2020)
- [K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables](https://mlsanity.com/paper/2110.05172/) (2021)
- [Back from the future: bidirectional CTC decoding using future information in speech recognition](https://mlsanity.com/paper/2110.03326/) (2021)

## Abstract (arXiv)

The performance of automatic speech recognition (ASR) models can be greatly improved by proper beam-search decoding with external language model (LM). There has been an increasing interest in Korean speech recognition, but not many studies have been focused on the decoding procedure. In this paper, we propose a Korean tokenization method for neural network-based LM used for Korean ASR. Although the common approach is to use the same tokenization method for external LM as the ASR model, we show that it may not be the best choice for Korean. We propose a new tokenization method that inserts a special token, SkipTC, when there is no trailing consonant in a Korean syllable. By utilizing the proposed SkipTC token, the input sequence for LM becomes very regularly patterned so that the LM can better learn the linguistic characteristics. Our experiments show that the proposed approach achieves a lower word error rate compared to the same LM model without SkipTC. In addition, we are the first to report the ASR performance for the recently introduced large-scale 7,600h Korean speech dataset.