An enhanced method for dialect transcription via error‐correcting thesaurus
Abstract Automatic speech recognition (ASR) has been widely used in the field of customer service, but the performance of general ASR in dialect transcription is not satisfactory, especially in Guangdong Province. Targeted training of ASR transcription engine will produce effect, but the training co...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-10-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12671 |
| _version_ | 1797661424062824448 |
|---|---|
| author | Xiaoliang Ma Congjian Deng Dequan Du Qingqi Pei |
| author_facet | Xiaoliang Ma Congjian Deng Dequan Du Qingqi Pei |
| author_sort | Xiaoliang Ma |
| collection | DOAJ |
| description | Abstract Automatic speech recognition (ASR) has been widely used in the field of customer service, but the performance of general ASR in dialect transcription is not satisfactory, especially in Guangdong Province. Targeted training of ASR transcription engine will produce effect, but the training cost is high, and it is not suitable for small‐scale training with multiple dialects and frequencies. The complaint problems in the customer service field have obvious clustering and are suitable for few‐shot and multi‐frequency training. In view of this, in the actual engineering application, the method of ASR transcribed into the dialect error correction thesaurus is tried to be used to replace the wrong words, and have achieved good results. The optimization technology after automatic speech transcription proposed in this study can improve the recognition accuracy of general ASR by 13.75% for dialect words. |
| first_indexed | 2024-03-11T18:44:20Z |
| format | Article |
| id | doaj.art-00a213af227741cda4c1262578bab5ec |
| institution | Directory Open Access Journal |
| issn | 1751-8628 1751-8636 |
| language | English |
| last_indexed | 2024-03-11T18:44:20Z |
| publishDate | 2023-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj.art-00a213af227741cda4c1262578bab5ec2023-10-12T05:26:30ZengWileyIET Communications1751-86281751-86362023-10-0117171984199710.1049/cmu2.12671An enhanced method for dialect transcription via error‐correcting thesaurusXiaoliang Ma0Congjian Deng1Dequan Du2Qingqi Pei3Guangzhou Institute of Technology, Xidian Univeristy Guangzhou ChinaGuangzhou Institute of Technology, Xidian Univeristy Guangzhou ChinaChina Telecom Co., Ltd. Guangzhou ChinaGuangzhou Institute of Technology, Xidian Univeristy Guangzhou ChinaAbstract Automatic speech recognition (ASR) has been widely used in the field of customer service, but the performance of general ASR in dialect transcription is not satisfactory, especially in Guangdong Province. Targeted training of ASR transcription engine will produce effect, but the training cost is high, and it is not suitable for small‐scale training with multiple dialects and frequencies. The complaint problems in the customer service field have obvious clustering and are suitable for few‐shot and multi‐frequency training. In view of this, in the actual engineering application, the method of ASR transcribed into the dialect error correction thesaurus is tried to be used to replace the wrong words, and have achieved good results. The optimization technology after automatic speech transcription proposed in this study can improve the recognition accuracy of general ASR by 13.75% for dialect words.https://doi.org/10.1049/cmu2.12671speech processingtelecommunication services |
| spellingShingle | Xiaoliang Ma Congjian Deng Dequan Du Qingqi Pei An enhanced method for dialect transcription via error‐correcting thesaurus IET Communications speech processing telecommunication services |
| title | An enhanced method for dialect transcription via error‐correcting thesaurus |
| title_full | An enhanced method for dialect transcription via error‐correcting thesaurus |
| title_fullStr | An enhanced method for dialect transcription via error‐correcting thesaurus |
| title_full_unstemmed | An enhanced method for dialect transcription via error‐correcting thesaurus |
| title_short | An enhanced method for dialect transcription via error‐correcting thesaurus |
| title_sort | enhanced method for dialect transcription via error correcting thesaurus |
| topic | speech processing telecommunication services |
| url | https://doi.org/10.1049/cmu2.12671 |
| work_keys_str_mv | AT xiaoliangma anenhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT congjiandeng anenhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT dequandu anenhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT qingqipei anenhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT xiaoliangma enhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT congjiandeng enhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT dequandu enhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus AT qingqipei enhancedmethodfordialecttranscriptionviaerrorcorrectingthesaurus |