Augmenting Polish Automatic Speech Recognition System With Synthetic Data

TL;DR

This paper demonstrates that augmenting Polish speech recognition models with synthetic data generated by a Voicebox-based system significantly improves their performance, with results validated in the Poleval 2024 challenge.

Contribution

The paper introduces a synthetic data augmentation pipeline for Polish ASR using Voicebox, enhancing Conformer and Whisper models' accuracy.

Findings

Synthetic data improves model performance

Significant results in Poleval 2024 competition

Effective Voicebox-based speech synthesis pipeline

Abstract

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.