Generating Synthetic Audio Data For Attention-based Speech Recognition Systems

Abstract

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 LibriSpee

Stats

• citations48
• S2 citations—
• github stars0
• HF likes0
• heat score12.68
• arxiv keyrossenbach2019generating

Related papers

• On The Effect Of Purely Synthetic Training Data For Different Automatic Speech Recognition Architectures (2024)0.00
• You Do Not Need More Data: Improving End-to-end Speech Recognition By Text-to-speech Data Augmentation (2020)11.49
• Comparing The Benefit Of Synthetic Training Data For Various Automatic Speech Recognition Architectures (2021)5.24
• On The Relevance Of Phoneme Duration Variability Of Synthesized Training Data For Automatic Speech Recognition (2023)2.26
• Tts-by-tts: Tts-driven Data Augmentation For Fast And High-quality Speech Synthesis (2020)9.59
• A Simple Baseline For Domain Adaptation In End To End ASR Systems Using Synthetic Data (2022)7.16
• Improving Accented Speech Recognition Using Data Augmentation Based On Unsupervised Text-to-speech Synthesis (2024)0.00
• Generating Data With Text-to-speech And Large-language Models For Conversational Speech Recognition (2024)6.34