T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5

Abstract: In Spoken language understanding (SLU), a natural solution is concatenating pre-trained speech models (e.g. HuBERT) and pretrained LLMs (PLM, e.g. T5). Most previous works use pretrained LLMs with subword-based tokenization. However, the granularity of input units affects the alignment of speech model outputs and LLM inputs, and PLM with character-based tokenization is underexplored. In this work, we conduct extensive studies on how PLMs with different tokenization strategies affect spoken language understanding task including spoken question answering (SQA) and speech translation (ST). We further extend the idea to create T5lephone(pronounced as telephone), a variant of T5 that is pretrained using phonemicized text. We initialize T5lephone with existing PLMs to pretrain it using relatively lightweight computational resources. We reached state-of-the-art on NMSQA, and the T5lephone model exceeds T5 with other types of units on end-to-end SQA and ST.