Chinese semantic and phonological information-based text proofreading model for speech recognition
To study the influence of Chinese Pinyin on detecting and correcting text errors in speech recognition, a text proofreading model based on Chinese semantic and phonological information was proposed.Five Pinyin coding methods were designed to construct the character-Pinyin embedding vector that was e...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2022-11-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022222/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539988680867840 |
|---|---|
| author | Meiyu ZHONG Peiliang WU Yan DOU Yi LIU Lingfu KONG |
| author_facet | Meiyu ZHONG Peiliang WU Yan DOU Yi LIU Lingfu KONG |
| author_sort | Meiyu ZHONG |
| collection | DOAJ |
| description | To study the influence of Chinese Pinyin on detecting and correcting text errors in speech recognition, a text proofreading model based on Chinese semantic and phonological information was proposed.Five Pinyin coding methods were designed to construct the character-Pinyin embedding vector that was employed as the input of the Seq2Seq model based on gated recurrent unit.At the same time, the attention mechanism was adopted to extract the Chinese semantic and phonological information of sentences to correct speech recognition errors.Aiming at the problem of insufficient labeled corpus, a data augmentation method was introduced, which could automatically obtain annotated corpora by exchanging the initials or finals of Chinese Pinyin.The experimental results on AISHELL-3’s public data show that phonological information is conducive to the text proofreading model to detect and correct text errors after speech recognition, and the proposed data augmentation method can improve the error detection performance of the model. |
| format | Article |
| id | doaj-art-b3ea0a02a99a446c94be6be8ed3e20c6 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2022-11-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-b3ea0a02a99a446c94be6be8ed3e20c62025-01-14T06:29:18ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2022-11-0143657959393573Chinese semantic and phonological information-based text proofreading model for speech recognitionMeiyu ZHONGPeiliang WUYan DOUYi LIULingfu KONGTo study the influence of Chinese Pinyin on detecting and correcting text errors in speech recognition, a text proofreading model based on Chinese semantic and phonological information was proposed.Five Pinyin coding methods were designed to construct the character-Pinyin embedding vector that was employed as the input of the Seq2Seq model based on gated recurrent unit.At the same time, the attention mechanism was adopted to extract the Chinese semantic and phonological information of sentences to correct speech recognition errors.Aiming at the problem of insufficient labeled corpus, a data augmentation method was introduced, which could automatically obtain annotated corpora by exchanging the initials or finals of Chinese Pinyin.The experimental results on AISHELL-3’s public data show that phonological information is conducive to the text proofreading model to detect and correct text errors after speech recognition, and the proposed data augmentation method can improve the error detection performance of the model.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022222/text proofreadingspeech recognitionPinyinattention mechanism |
| spellingShingle | Meiyu ZHONG Peiliang WU Yan DOU Yi LIU Lingfu KONG Chinese semantic and phonological information-based text proofreading model for speech recognition Tongxin xuebao text proofreading speech recognition Pinyin attention mechanism |
| title | Chinese semantic and phonological information-based text proofreading model for speech recognition |
| title_full | Chinese semantic and phonological information-based text proofreading model for speech recognition |
| title_fullStr | Chinese semantic and phonological information-based text proofreading model for speech recognition |
| title_full_unstemmed | Chinese semantic and phonological information-based text proofreading model for speech recognition |
| title_short | Chinese semantic and phonological information-based text proofreading model for speech recognition |
| title_sort | chinese semantic and phonological information based text proofreading model for speech recognition |
| topic | text proofreading speech recognition Pinyin attention mechanism |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022222/ |
| work_keys_str_mv | AT meiyuzhong chinesesemanticandphonologicalinformationbasedtextproofreadingmodelforspeechrecognition AT peiliangwu chinesesemanticandphonologicalinformationbasedtextproofreadingmodelforspeechrecognition AT yandou chinesesemanticandphonologicalinformationbasedtextproofreadingmodelforspeechrecognition AT yiliu chinesesemanticandphonologicalinformationbasedtextproofreadingmodelforspeechrecognition AT lingfukong chinesesemanticandphonologicalinformationbasedtextproofreadingmodelforspeechrecognition |