Discrete Multimodal Transformers With A Pretrained Large Language Model For Mixed-supervision Speech Processing

Trinh Viet Anh, Southwell Rosy, Guan Yiwen, He Xinlu, Wang Zhiyong, Whitehill Jacob. Arxiv 2024

[Paper]    
Masked Language Model Model Architecture Multimodal Models Pretraining Methods Tokenization Training Techniques Transformer

Recent work on discrete speech tokenization has paved the way for models that can seamlessly perform multiple tasks across modalities, e.g., speech recognition, text to speech, speech to speech translation. Moreover, large language models (LLMs) pretrained from vast text corpora contain rich linguistic information that can improve accuracy in a variety of tasks. In this paper, we present a decoder-only Discrete Multimodal Language Model (DMLM), which can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision). We explore several critical aspects of discrete multi-modal models, including the loss function, weight initialization, mixed training supervision, and codebook. Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training. Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.

Similar Work