Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks

no code implementations • 24 Feb 2024 • Duo Ma, Xianghu Yue, Junyi Ao, Xiaoxue Gao, Haizhou Li

In this paper, we investigate a new way to pre-train such a joint speech-text model to learn enhanced speech representations and benefit various speech-related downstream tasks.

Pseudo Label Self-Supervised Learning

Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech

no code implementations • 22 Jul 2021 • Duo Ma, Nana Hou, Van Tung Pham, HaiHua Xu, Eng Siong Chng

One of the advantage of the proposed method is that the entire system can be trained from scratch.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3