SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data-Reference-Cited by-同舟云学术

SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data

Published:2024 Issue: Volume:32 Page:2177-2187
ISSN:2329-9290
Container-title:IEEE/ACM Transactions on Audio, Speech, and Language Processing
language:
Short-container-title:IEEE/ACM Trans. Audio Speech Lang. Process.

Author:

Zhang Ziqiang¹^ORCID,Chen Sanyuan²^ORCID,Zhou Long³^ORCID,Wu Yu³^ORCID,Ren Shuo³,Liu Shujie³,Yao Zhuoyuan³,Gong Xun³,Dai Lirong¹^ORCID,Li Jinyu⁴^ORCID,Wei Furu³

Affiliation:

1. National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China

2. Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

3. Microsoft Research Asia, Beijing, China

4. Microsoft Corporation, Redmond, WA, USA

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/6570655/10304349/10476749.pdf?arnumber=10476749

Reference52 articles.

1. Unified language model pre-training for natural language understanding and generation;Dong,2019

2. wav2vec: Unsupervised Pre-Training for Speech Recognition

3. HuBERT: Self-supervised speech representation learning by masked prediction of hidden units;Hsu,2021

4. Broca and Wernicke are dead, or moving past the classic model of language neurobiology

Cited by 7 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Translatotron 3: Speech to Speech Translation with Monolingual Data;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. M2BART: Multilingual and Multimodal Encoder-Decoder Pre-Training for Any-to-Any Machine Translation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Typing on Any Surface: Real-Time Keystroke Detection in Augmented Reality;2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR);2024-01-17