An effective contextual language modeling framework for speech summarization with augmented features

Shi Yan Weng, Tien Hong Lo, Berlin Chen

研究成果: 書貢獻/報告類型會議論文篇章

1 引文 斯高帕斯(Scopus)

摘要

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural network-based methods to extractive speech summarization. More recently, the Bidirectional Encoder Representations from Transformers (BERT) model was proposed and has achieved record-breaking success on many natural language processing (NLP) tasks such as question answering and language understanding. In view of this, we in this paper contextualize and enhance the state-of-the-art BERT-based model for speech summarization, while its contributions are at least three-fold. First, we explore the incorporation of confidence scores into sentence representations to see if such an attempt could help alleviate the negative effects caused by imperfect automatic speech recognition (ASR). Secondly, we also augment the sentence embeddings obtained from BERT with extra structural and linguistic features, such as sentence position and inverse document frequency (IDF) statistics. Finally, we validate the effectiveness of our proposed method on a benchmark dataset, in comparison to several classic and celebrated speech summarization methods.

原文英語
主出版物標題28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings
發行者European Signal Processing Conference, EUSIPCO
頁面316-320
頁數5
ISBN(電子)9789082797053
DOIs
出版狀態已發佈 - 2021 一月 24
對外發佈Yes
事件28th European Signal Processing Conference, EUSIPCO 2020 - Amsterdam, 荷兰
持續時間: 2020 八月 242020 八月 28

出版系列

名字European Signal Processing Conference
2021-January
ISSN(列印)2219-5491

會議

會議28th European Signal Processing Conference, EUSIPCO 2020
國家荷兰
城市Amsterdam
期間2020/08/242020/08/28

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

指紋 深入研究「An effective contextual language modeling framework for speech summarization with augmented features」主題。共同形成了獨特的指紋。

引用此