arXiv Open Access 2024

Augmenting Polish Automatic Speech Recognition System With Synthetic Data

Łukasz Bondaruk Jakub Kubiak Mateusz Czyżnikiewicz

Lihat Sumber

Abstrak

This paper presents a system developed for submission to Poleval 2024, Task 3: Polish Automatic Speech Recognition Challenge. We describe Voicebox-based speech synthesis pipeline and utilize it to augment Conformer and Whisper speech recognition models with synthetic data. We show that addition of synthetic speech to training improves achieved results significantly. We also present final results achieved by our models in the competition.

Topik & Kata Kunci

eess.AS cs.SD

Penulis (3)

Łukasz Bondaruk

Jakub Kubiak

Mateusz Czyżnikiewicz

Format Sitasi

APA MLA BibTeX

Bondaruk, Ł., Kubiak, J., Czyżnikiewicz, M. (2024). Augmenting Polish Automatic Speech Recognition System With Synthetic Data. https://arxiv.org/abs/2410.22903

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓