data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup

Autor:	Lodagala, Vasista Sai, Ghosh, Sreyan, Umesh, S.
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled data are limited. Building on the recently introduced data2vec, we introduce additional modules to the data2vec framework that leverage the benefit of data augmentations, quantized representations, and clustering. The interaction between these modules helps solve the cross-contrastive loss as an additional self-supervised objective. data2vec-aqc achieves up to 14.1% and 20.9% relative WER improvement over the existing state-of-the-art data2vec system over the test-clean and test-other sets, respectively of LibriSpeech, without the use of any language model (LM). Our proposed model also achieves up to 17.8\% relative WER gains over the baseline data2vec when fine-tuned on a subset of the Switchboard dataset. Code: https://github.com/Speech-Lab-IITM/data2vec-aqc. Comment: Accepted to ICASSP 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2211.01246 Zobrazit plný text záznamu View this record from Arxiv