CTCBERT: Advancing Hidden-unit BERT with CTC Objectives

Autor:	Fan, Ruchao, Wang, Yiming, Gaur, Yashesh, Li, Jinyu
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the model training with the Connectionist Temporal Classification (CTC) objective after removing duplicated IDs in each masked region. The idea stems from the observation that there can be significant errors in alignments when using clustered or aligned IDs. CTC learns alignments implicitly, indicating that learning with CTC can be more flexible when misalignment exists. We examine CTCBERT on IDs from HuBERT Iter1, HuBERT Iter2, and PBERT. The CTC training brings consistent improvements compared to the CE training. Furthermore, when loading blank-related parameters during finetuning, slight improvements are observed. Evaluated on the Librispeech 960-100h setting, the relative WER improvements of CTCBERT are 2%-11% over HuBERT and PERT on test-other data. Comment: Accepted to ICASSP2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2210.08603 Zobrazit plný text záznamu View this record from Arxiv