Cross-sentence Neural Language Models for Conversational Speech Recognition

Shih Hsuan Chiu, Tien Hang 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

An important research direction in automatic speech recognition (ASR) has centered around the development of effective methods to rerank the output hypotheses of an ASR system with more sophisticated language models (LMs) for further gains. A current mainstream school of thoughts for ASR N-best hypothesis reranking is to employ a recurrent neural network (RNN)-based LM or its variants, with performance superiority over the conventional n-gram LMs across a range of ASR tasks. In real scenarios such as a long conversation, a sequence of consecutive sentences may jointly contain ample cues of conversation-level information such as topical coherence, lexical entrainment and adjacency pairs, which however remains to be underexplored. In view of this, we first formulate ASR N-best reranking as a prediction problem, putting forward an effective cross-sentence neural LM approach that reranks the ASR N-best hypotheses of an upcoming sentence by taking into consideration the word usage in its precedent sentences. Furthermore, we also explore to extract task-specific global topical information of the cross-sentence history in an unsupervised manner for better ASR performance. Extensive experiments conducted on the AMI conversational benchmark corpus indicate the effectiveness and feasibility of our methods in comparison to several state-of-the-art reranking methods.

原文英語
主出版物標題IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9780738133669
DOIs
出版狀態已發佈 - 2021 7月 18
事件2021 International Joint Conference on Neural Networks, IJCNN 2021 - Virtual, Shenzhen, 中国
持續時間: 2021 7月 182021 7月 22

出版系列

名字Proceedings of the International Joint Conference on Neural Networks
2021-July

會議

會議2021 International Joint Conference on Neural Networks, IJCNN 2021
國家/地區中国
城市Virtual, Shenzhen
期間2021/07/182021/07/22

ASJC Scopus subject areas

  • 軟體
  • 人工智慧

指紋

深入研究「Cross-sentence Neural Language Models for Conversational Speech Recognition」主題。共同形成了獨特的指紋。

引用此