BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model

29 October 2022

Papers citing "BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model"

7 / 7 papers shown

Title
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems Takuma Udagawa Masayuki Suzuki Gakuto Kurata Masayasu Muraoka G. Saon 15 2 0 07 Sep 2023
ASR Rescoring and Confidence Estimation with ELECTRA Hayato Futami H. Inaguma Masato Mimura S. Sakai Tatsuya Kawahara KELM 54 20 0 05 Oct 2021
Intermediate Loss Regularization for CTC-based Speech Recognition Jaesong Lee Shinji Watanabe 111 135 0 05 Feb 2021
Speech Recognition by Simply Fine-tuning BERT Wen-Chin Huang Chia-Hua Wu Shang-Bao Luo Kuan-Yu Chen Hsin-Min Wang T. Toda 62 28 0 30 Jan 2021
Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition Cheng Yi Shiyu Zhou Bo Xu 47 40 0 17 Jan 2021
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters Hicham El Boukkouri Olivier Ferret Thomas Lavergne Hiroshi Noji Pierre Zweigenbaum Junichi Tsujii 66 155 0 20 Oct 2020
Transformer ASR with Contextual Block Processing E. Tsunoo Yosuke Kashiwagi Toshiyuki Kumakura Shinji Watanabe 51 64 0 16 Oct 2019