A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives
This addresses speech recognition for multilingual oral history archives, which is important for cultural heritage preservation, but appears incremental as it applies existing methods to a new dataset.
The paper compared monolingual and multilingual Wav2Vec models for automatic speech recognition on a mixed-language oral history archive, finding that monolingual models generally performed better despite the multilingual content.
In this paper, we are comparing monolingual Wav2Vec 2.0 models with various multilingual models to see whether we could improve speech recognition performance on a unique oral history archive containing a lot of mixed-language sentences. Our main goal is to push forward research on this unique dataset, which is an extremely valuable part of our cultural heritage. Our results suggest that monolingual speech recognition models are, in most cases, superior to multilingual models, even when processing the oral history archive full of mixed-language sentences from non-native speakers. We also performed the same experiments on the public CommonVoice dataset to verify our results. We are contributing to the research community by releasing our pre-trained models to the public.