Task Arithmetic Can Mitigate Synthetic-to-real Gap In Automatic Speech Recognition

Abstract

Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains. However, existing methods suffer in performance when they fine-tune an automatic speech recognition (ASR) model on synthetic data as they suffer from the distributional shift commonly referred to as the synthetic-to-real gap. In this paper, we find that task vector arithmetic is effective at mitigating this gap. Our proposed method, SYN2REAL task vector, shows an average improvement of 10.03% improvement in word error rate over baselines on the SLURP dataset. Additionally, we show that an average of SYN2REAL task vectors, when we have real speeches from multiple different domains, can further adapt the original ASR model to perform better on the target text domain.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysu2024task

Related papers

• On The Effect Of Purely Synthetic Training Data For Different Automatic Speech Recognition Architectures (2024)0.00
• 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
• Generating Synthetic Audio Data For Attention-based Speech Recognition Systems (2019)12.68
• Enhancing Synthetic Training Data For Speech Commands: From Asr-based Filtering To Domain Adaptation In SSL Latent Space (2024)0.00
• Training Data Augmentation For Dysarthric Automatic Speech Recognition By Text-to-dysarthric-speech Synthesis (2024)10.48
• Task Arithmetic For Language Expansion In Speech Translation (2024)0.00
• Using Synthetic Audio To Improve The Recognition Of Out-of-vocabulary Words In End-to-end ASR Systems (2020)12.33