Effective Cross-Utterance Language Modeling for Conversational Speech Recognition

Bi Cheng Yan, Hsin Wei Wang, Shih Hsuan Chiu, Hsuan Sheng Chiu, 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

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context information with a recurrent neural network or long short-term memory language model (LM) may suffer from the recent bias while excluding the long-range context. In order to capture the long-term semantic interactions among words and across utterances, we put forward disparate conversation history fusion methods for language modeling in automatic speech recognition (ASR) of conversational speech. Furthermore, a novel audio-fusion mechanism is introduced, which manages to fuse and utilize the acoustic embeddings of a current utterance and the semantic content of its corresponding conversation history in a cooperative way. To flesh out our ideas, we frame the ASR N-best hypothesis rescoring task as a prediction problem, leveraging BERT, an iconic pre-trained LM, as the ingredient vehicle to facilitate selection of the oracle hypothesis from a given N-best hypothesis list. Empirical experiments conducted on the AMI benchmark dataset seem to demonstrate the feasibility and efficacy of our methods in relation to some current top-of-line methods. The proposed methods not only achieve significant inference time reduction but also improve the ASR performance for conversational speech.

原文英語
主出版物標題2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728186719
DOIs
出版狀態已發佈 - 2022
事件2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, 意大利
持續時間: 2022 7月 182022 7月 23

出版系列

名字Proceedings of the International Joint Conference on Neural Networks
2022-July

會議

會議2022 International Joint Conference on Neural Networks, IJCNN 2022
國家/地區意大利
城市Padua
期間2022/07/182022/07/23

ASJC Scopus subject areas

  • 軟體
  • 人工智慧

指紋

深入研究「Effective Cross-Utterance Language Modeling for Conversational Speech Recognition」主題。共同形成了獨特的指紋。

引用此