Speech_ssl
01 Aug 2023title: (yet) Self-Supervised Learning (SSL) for Speech categories: Speech tag: [speech]
toc: true toc_sticky: true
not_ready: false not_implemented: false
comment: false
< 목차 >
한번 쓰긴 써야되는데...
양이 너무 방대하다...
일단 시작...
Introduction
Why Self-Supervised Learning (SSL) ?
Representation Learning
Advances of SSL for Speech
2023년까지 Speech를 위한 SSL method들이 무수히 많이 제안되어 왔습니다. 본 Post에서는 그 중 핵심적인 논문 몇가지만 디테일하게 살펴볼 것인데 그 전에 간단하게 발전사를 훑고 넘어가보려고 합니다.
Fig. 2015년 부터 2022년 까지의 발전사.
(2020) Wav2Vec 2.0
asd
References
- Papers
- Core
- Representation Learning with Contrastive Predictive Coding
- wav2vec: Unsupervised Pre-training for Speech Recognition
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
- data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
- Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
- W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
- Self-supervised Learning with Random-projection Quantizer for Speech Recognition
- Additional (+ Other domain SSL)
- Core
- Lecture and Seminar
- Blogs and Others