基于互补神经语言模型大集合的点阵评分

A. Ogawa, Naohiro Tawara, Marc Delcroix, S. Araki
{"title":"基于互补神经语言模型大集合的点阵评分","authors":"A. Ogawa, Naohiro Tawara, Marc Delcroix, S. Araki","doi":"10.1109/ICASSP43922.2022.9747745","DOIUrl":null,"url":null,"abstract":"We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectiveness of combining a small number of NLMs. In contrast, in this study, we combine up to eight NLMs, i.e., forward/backward long short-term memory/Transformer-LMs that are trained with two different random initialization seeds. We combine these NLMs through iterative lattice generation. Since these NLMs work complementarily with each other, by combining them one by one at each rescoring iteration, language scores attached to given lattice arcs can be gradually refined. Consequently, errors of the ASR hypotheses can be gradually reduced. We also investigate the effectiveness of carrying over contextual information (previous rescoring results) across a lattice sequence of a long speech such as a lecture speech. In experiments using a lecture speech corpus, by combining the eight NLMs and using context carry-over, we obtained a 24.4% relative word error rate reduction from the ASR 1-best baseline. For further comparison, we performed simultaneous (i.e., non-iterative) NLM combination and 100-best rescoring using the large ensemble of NLMs, which confirmed the advantage of lattice rescoring with iterative NLM combination.","PeriodicalId":272439,"journal":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models\",\"authors\":\"A. Ogawa, Naohiro Tawara, Marc Delcroix, S. Araki\",\"doi\":\"10.1109/ICASSP43922.2022.9747745\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectiveness of combining a small number of NLMs. In contrast, in this study, we combine up to eight NLMs, i.e., forward/backward long short-term memory/Transformer-LMs that are trained with two different random initialization seeds. We combine these NLMs through iterative lattice generation. Since these NLMs work complementarily with each other, by combining them one by one at each rescoring iteration, language scores attached to given lattice arcs can be gradually refined. Consequently, errors of the ASR hypotheses can be gradually reduced. We also investigate the effectiveness of carrying over contextual information (previous rescoring results) across a lattice sequence of a long speech such as a lecture speech. In experiments using a lecture speech corpus, by combining the eight NLMs and using context carry-over, we obtained a 24.4% relative word error rate reduction from the ASR 1-best baseline. For further comparison, we performed simultaneous (i.e., non-iterative) NLM combination and 100-best rescoring using the large ensemble of NLMs, which confirmed the advantage of lattice rescoring with iterative NLM combination.\",\"PeriodicalId\":272439,\"journal\":{\"name\":\"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"volume\":\"68 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-05-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP43922.2022.9747745\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP43922.2022.9747745","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

我们研究了在自动语音识别(ASR)假设上使用大量高级神经语言模型(nlm)进行点阵评分的有效性。先前的研究已经报道了联合使用少量nlm的有效性。相比之下,在本研究中,我们结合了多达8个nlm,即前向/后向长短期记忆/转换lms,它们由两种不同的随机初始化种子训练。我们通过迭代晶格生成来组合这些nlm。由于这些nlm相互补充,通过在每次评分迭代中将它们一个接一个地组合在一起,可以逐渐改进给定点阵弧的语言分数。因此,ASR假设的误差可以逐渐减小。我们还研究了在长演讲(如演讲)的晶格序列中传递上下文信息(先前的评分结果)的有效性。在使用演讲语料库的实验中,通过结合8个nlm并使用上下文结转,我们获得了相对于ASR 1最佳基线的24.4%的相对单词错误率降低。为了进一步比较,我们使用NLM的大集合进行了同时(即非迭代)NLM组合和100-best评分,这证实了迭代NLM组合的点阵评分的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models
We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectiveness of combining a small number of NLMs. In contrast, in this study, we combine up to eight NLMs, i.e., forward/backward long short-term memory/Transformer-LMs that are trained with two different random initialization seeds. We combine these NLMs through iterative lattice generation. Since these NLMs work complementarily with each other, by combining them one by one at each rescoring iteration, language scores attached to given lattice arcs can be gradually refined. Consequently, errors of the ASR hypotheses can be gradually reduced. We also investigate the effectiveness of carrying over contextual information (previous rescoring results) across a lattice sequence of a long speech such as a lecture speech. In experiments using a lecture speech corpus, by combining the eight NLMs and using context carry-over, we obtained a 24.4% relative word error rate reduction from the ASR 1-best baseline. For further comparison, we performed simultaneous (i.e., non-iterative) NLM combination and 100-best rescoring using the large ensemble of NLMs, which confirmed the advantage of lattice rescoring with iterative NLM combination.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信