Innovative Bert-Based Reranking Language Models for Speech Recognition

Shih Hsuan Chiu, Berlin Chen

研究成果: 書貢獻/報告類型會議論文篇章

摘要

More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such as question answering and language understanding, due mainly to its effective pre-training then fine-tuning paradigm as well as strong local contextual modeling ability. In view of the above, this paper presents a novel instantiation of the BERT-based contextualized language models (LMs) for use in reranking of N-best hypotheses produced by automatic speech recognition (ASR). To this end, we frame N-best hypothesis reranking with BERT as a prediction problem, which aims to predict the oracle hypothesis that has the lowest word error rate (WER) given the N-best hypotheses (denoted by PBERT). In particular, we also explore to capitalize on task-specific global topic information in an unsupervised manner to assist PBERT in N-best hypothesis reranking (denoted by TPBERT). Extensive experiments conducted on the AMI benchmark corpus demonstrate the effectiveness and feasibility of our methods in comparison to the conventional autoregressive models like the recurrent neural network (RNN) and a recently proposed method that employed BERT to compute pseudo-log-likelihood (PLL) scores for N-best hypothesis reranking.

原文英語
主出版物標題2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面266-271
頁數6
ISBN(電子)9781728170664
DOIs
出版狀態已發佈 - 2021 一月 19
事件2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Virtual, Shenzhen, 中国
持續時間: 2021 一月 192021 一月 22

出版系列

名字2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings

會議

會議2021 IEEE Spoken Language Technology Workshop, SLT 2021
國家中国
城市Virtual, Shenzhen
期間2021/01/192021/01/22

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

指紋 深入研究「Innovative Bert-Based Reranking Language Models for Speech Recognition」主題。共同形成了獨特的指紋。

引用此