https://scholars.lib.ntu.edu.tw/handle/123456789/580914
標題: | SpeechBERT: An audio-and-text jointly learned language model for end-to-end spoken question answering | 作者: | Chuang Y.-S Liu C.-L Lee H.-Y HUNG-YI LEE LIN-SHAN LEE |
關鍵字: | Text processing; Audio data; Cascade architecture; Conventional approach; End-to-end models; Extract informations; Language model; Question Answering; Spoken language understanding; Speech communication | 公開日期: | 2020 | 卷: | 2020-October | 起(迄)頁: | 4168-4172 | 來源出版物: | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 摘要: | While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning from the very successful BERT model for various text processing tasks, here we proposed an audio-and-text jointly learned SpeechBERT model. This model outperformed the conventional approach of cascading ASR with the following text question answering (TQA) model on datasets including ASR errors in answer spans, because the end-to-end model was shown to be able to extract information out of audio data before ASR produced errors. When ensembling the proposed end-to-end model with the cascade architecture, even better performance was achieved. In addition to the potential of end-to-end SQA, the SpeechBERT can also be considered for many other spoken language understanding tasks just as BERT for many text processing tasks. Copyright ? 2020 ISCA |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098160093&doi=10.21437%2fInterspeech.2020-1570&partnerID=40&md5=c52d894fbe4e38dcbd5d5978acd801a8 https://scholars.lib.ntu.edu.tw/handle/123456789/580914 |
ISSN: | 2308457X | DOI: | 10.21437/Interspeech.2020-1570 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。