@article{zhang2024speechlm,
author = {Zhang, Ziqiang and Chen, Sanyuan and Zhou, Long and Wu, Yu and Ren, Shuo and Liu, Shujie and Yao, Zhuoyuan and Gong, Xun and Dai, Lirong and Li, Jinyu and Wei, Furu},
title = {SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data},
year = {2024},
month = {March},
abstract = {How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and L anguage M odel ( SpeechLM ) to explicitly align speech and text pre-training with a pre-defined unified discrete representation. Specifically, we introduce two alternative discrete tokenizers to bridge the speech and text modalities, including phoneme-unit and hidden-unit tokenizers, which can be trained using unpaired speech or a small amount of paired speech-text data. Based on the trained tokenizers, we convert the unlabeled speech and text data into tokens of phoneme units or hidden units. The pre-training objective is designed to unify the speech and the text into the same discrete semantic space with a unified Transformer network. We evaluate SpeechLM on various spoken language processing tasks including speech recognition, speech translation, and universal representation evaluation framework SUPERB, demonstrating significant improvements on content-related tasks.},
url = {http://approjects.co.za/?big=en-us/research/publication/speechlm-enhanced-speech-pre-training-with-unpaired-textual-data/},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
}