Exploration of Adapter for Noise Robust Automatic Speech Recognition
This work addresses noise robustness in ASR systems, which is crucial for real-world applications, but it is incremental as it builds on existing adapter techniques.
The study tackled adapting automatic speech recognition systems to unseen noise environments using adapters, finding that inserting adapters in shallow layers is effective and integrating them with speech enhancement systems yields substantial improvements, with experiments on the CHiME-4 dataset.
Adapting an automatic speech recognition (ASR) system to unseen noise environments is crucial. Integrating adapters into neural networks has emerged as a potent technique for transfer learning. This study thoroughly investigates adapter-based ASR adaptation in noisy environments. We conducted experiments using the CHiME--4 dataset. The results show that inserting the adapter in the shallow layer yields superior effectiveness, and there is no significant difference between adapting solely within the shallow layer and adapting across all layers. The simulated data helps the system to improve its performance under real noise conditions. Nonetheless, when the amount of data is the same, the real data is more effective than the simulated data. Multi-condition training is still useful for adapter training. Furthermore, integrating adapters into speech enhancement-based ASR systems yields substantial improvements.