Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
This addresses data scarcity in speech recognition for low-resource environments, though it is incremental as it builds on existing TTS and ASR methods.
The paper tackled the problem of low-resource speech recognition by using synthetic audio from a TTS system trained on ASR corpora to enhance attention-based ASR systems, achieving up to 33% relative WER improvement in low-resource settings and up to 5% on larger datasets.
Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS system trained only on the ASR corpora itself. ASR and TTS systems are built separately to show that text-only data can be used to enhance existing end-to-end ASR systems without the necessity of parameter or architecture changes. We compare our method with language model integration of the same text data and with simple data augmentation methods like SpecAugment and show that performance improvements are mostly independent. We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50\%. We also show improvements of up to 5% relative WER over our most recent ASR baseline on LibriSpeech-960h.