paper-with-me

홈 › Papers

Korean Tokenization for Beam Search Rescoring in Speech Recognition

2022-02-22 · Kyuhong Shim, Hyewon Bae, Wonyong Sung

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.

📄 PDF Abstract BibTeX arXiv:2203.03583

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

ProGRes: Prompted Generative Rescoring on ASR n-Best

2024-08-30 · Ada Defne Tur, Adel Moumen, Mirco Ravanelli

Large Language Models (LLMs) have shown their ability to improve the performance of speech recognizers by effectively rescoring the n-best hypotheses generated during the beam search process. However, the best way to exp…

speech-recognitionSpeech Recognition

An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks

2020-10-06 · Asian Chapter of the Association for Computational Linguistics 2020 · Kyubyong Park, Joohong Lee, Seongbo Jang, Dawoon Jung

Typically, tokenization is the very first step in most text processing works. As a token serves as an atomic unit that embeds the contextual information of text, how to define a token plays a decisive role in the perform…

Machine TranslationNatural Language UnderstandingSegmentationTranslation

Discriminative Segmental Cascades for Feature-Rich Phone Recognition

2015-07-22 · Hao Tang, Weiran Wang, Kevin Gimpel, Karen Livescu

Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognition via both lattice rescoring and first-p…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition+1

Korean-English Machine Translation with Multiple Tokenization Strategy

2021-05-29 · Dojun Park, Youngjin Jang, Harksoo Kim

This work was conducted to find out how tokenization methods affect the training results of machine translation models. In this work, alphabet tokenization, morpheme tokenization, and BPE tokenization were applied to Kor…

Machine TranslationTranslation

Should we find another model?: Improving Neural Machine Translation Performance with ONE-Piece Tokenization Method without Model Modification

2021-06-01 · NAACL 2021 4 · Chanjun Park, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim

Most of the recent Natural Language Processing(NLP) studies are based on the Pretrain-Finetuning Approach (PFA), but in small and medium-sized enterprises or companies with insufficient hardware there are many limitation…

Machine TranslationmodelTranslation