{"title":"带纠错模块的非自回归语音识别","authors":"Yukun Qian, Xuyi Zhuang, Zehua Zhang, Lianyu Zhou, Xu Lin, Mingjiang Wang","doi":"10.23919/APSIPAASC55919.2022.9980031","DOIUrl":null,"url":null,"abstract":"Autoregressive models have achieved good performance in the field of speech recognition. However, the autore-gressive model uses recursive decoding and beam search in the inference stage, which leads to its slow inference speed. On the other hand, the non-autoregressive model naturally cannot utilize the context since all tokens are output at one time. To solve this problem, we propose a position-dependent non-autoregressive model. And in order to make better use of contextual information, we propose a pre-trained language model for speech recognition, which is placed behind the non-autoregressive model as an error correction module. In this way, we exchanged a smaller amount of calculation for the improvement of the recognition rate. Our method not only greatly reduces the computational cost, but also maintains a good recognition rate. We tested our model on the public Chinese speech corpus AISHELL-1. Our model achieves a 6.5% character error rate while the real-time factor is only 0.0022, which is 1/17 of the autoregressive model.","PeriodicalId":382967,"journal":{"name":"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"29 7","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Non-Autoregressive Speech Recognition with Error Correction Module\",\"authors\":\"Yukun Qian, Xuyi Zhuang, Zehua Zhang, Lianyu Zhou, Xu Lin, Mingjiang Wang\",\"doi\":\"10.23919/APSIPAASC55919.2022.9980031\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Autoregressive models have achieved good performance in the field of speech recognition. However, the autore-gressive model uses recursive decoding and beam search in the inference stage, which leads to its slow inference speed. On the other hand, the non-autoregressive model naturally cannot utilize the context since all tokens are output at one time. To solve this problem, we propose a position-dependent non-autoregressive model. And in order to make better use of contextual information, we propose a pre-trained language model for speech recognition, which is placed behind the non-autoregressive model as an error correction module. In this way, we exchanged a smaller amount of calculation for the improvement of the recognition rate. Our method not only greatly reduces the computational cost, but also maintains a good recognition rate. We tested our model on the public Chinese speech corpus AISHELL-1. Our model achieves a 6.5% character error rate while the real-time factor is only 0.0022, which is 1/17 of the autoregressive model.\",\"PeriodicalId\":382967,\"journal\":{\"name\":\"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)\",\"volume\":\"29 7\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/APSIPAASC55919.2022.9980031\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/APSIPAASC55919.2022.9980031","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Non-Autoregressive Speech Recognition with Error Correction Module
Autoregressive models have achieved good performance in the field of speech recognition. However, the autore-gressive model uses recursive decoding and beam search in the inference stage, which leads to its slow inference speed. On the other hand, the non-autoregressive model naturally cannot utilize the context since all tokens are output at one time. To solve this problem, we propose a position-dependent non-autoregressive model. And in order to make better use of contextual information, we propose a pre-trained language model for speech recognition, which is placed behind the non-autoregressive model as an error correction module. In this way, we exchanged a smaller amount of calculation for the improvement of the recognition rate. Our method not only greatly reduces the computational cost, but also maintains a good recognition rate. We tested our model on the public Chinese speech corpus AISHELL-1. Our model achieves a 6.5% character error rate while the real-time factor is only 0.0022, which is 1/17 of the autoregressive model.