w2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training-Reference-Cited by-同舟云学术

w2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Chung Yu-An¹,Zhang Yu²,Han Wei²,Chiu Chung-Cheng²,Qin James²,Pang Ruoming²,Wu Yonghui²

Affiliation:

1. MIT Computer Science and Artificial Intelligence Laboratory

2. Google Brain

Publisher

IEEE

Link

Reference42 articles.

2. Adafactor: Adaptive learning rates with sublinear memory cost;shazeer;ICML,0

3. Batch normalization: Accelerating deep network training by reducing internal covariate shift;ioffe;ICML,0

4. Searching for activation functions;ramachandran;ArXiv Preprint,2017

Cited by 133 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. Speaker and Digit Representation based Voice OTP System;2024 International Conference on Signal Processing and Communications (SPCOM);2024-07-01

2. Generative Spoken Language Modeling with Quantized Feature Enhancement;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. AudioPalette: Generating Soundtracks through Feature Extraction from Images;2024 International Conference on Inventive Computation Technologies (ICICT);2024-04-24