1. Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech
- Author
-
Jan Lehečka, Jan Švec, Ales Prazak, and Josef Psutka
- Subjects
FOS: Computer and information sciences ,Sound (cs.SD) ,ComputingMethodologies_PATTERNRECOGNITION ,Computer Science - Computation and Language ,Audio and Speech Processing (eess.AS) ,FOS: Electrical engineering, electronic engineering, information engineering ,Computation and Language (cs.CL) ,Computer Science - Sound ,speech recognition, audio transformers, Wav2Vec ,Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech recognition tasks using a combination of in-domain data and almost 6 thousand hours of out-of-domain transcribed speech. We are presenting a large palette of experiments with various fine-tuning setups evaluated on two public datasets (CommonVoice and VoxPopuli) and one extremely challenging dataset from the MALACH project. Our results show that monolingual Wav2Vec 2.0 models are robust ASR systems, which can take advantage of large labeled and unlabeled datasets and successfully compete with state-of-the-art LVCSR systems. Moreover, Wav2Vec models proved to be good zero-shot learners when no training data are available for the target ASR task., to be published in Proceedings of INTERSPEECH 2022
- Published
- 2022