2022/07/01 by Mitchell DeHaven, DeHaven, Mitchell, Jayadev Billa +1 · 2 citations
Computer Science · #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2207.00659
Submitted to Interspeech 2022
arxiv created 2022/07/01 · arxiv updated 2022/07/05
Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based pretrained XLSR-53 model across many languages when fine-tuned with available labeled data. However, the performance from finetuning these models can be dependent on the amount of in-language or similar-to-in-language data included in the pretraining dataset. In this paper we investigate continued pretraining (CoPT) with unlabeled in-language audio data on the XLSR-53 pretrained model in several low-resource languages. CoPT is more computationally efficient than semi-supervised training (SST), the standard approach of utilizing unlabeled data in ASR, since it omits the need for pseudo-labeling of the unlabeled data. We show CoPT results in word error rates (WERs), equal to or slightly better than using SST. In addition, we show that using the CoPT model for pseudo-labeling, and using these labels in SST, results in further improvements in WER.